© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 20604
    Prev
    Next
    INDEX
    Explanations

    isco

    np_max-act · gemini-2.0-flash

    proper nouns, especially capitalized names of people, places, and titled entities.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    语
    -0.07
     frac
    -0.06
    .Th
    -0.06
     TableRow
    -0.06
    ʧ
    -0.06
    น
    -0.06
     suppl
    -0.06
     Conj
    -0.06
    _contract
    -0.06
    Sil
    -0.06
    POSITIVE LOGITS
    .nz
    0.08
     отправ
    0.07
     passe
    0.07
    稳定
    0.07
     بأنه
    0.07
     Syria
    0.07
    —even
    0.06
     查询
    0.06
     converged
    0.06
    Cycle
    0.06
    Activations Density 0.729%

    No Known Activations