© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 45217
    Prev
    Next
    INDEX
    Explanations

    active

    np_max-act · gemini-2.0-flash
    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
     Sergio
    -0.07
    受理
    -0.07
     prime
    -0.07
     eius
    -0.07
    Elim
    -0.07
     Super
    -0.06
     agr
    -0.06
     safeguard
    -0.06
    ˻
    -0.06
     KO
    -0.06
    POSITIVE LOGITS
     wf
    0.07
    ставка
    0.07
     drafts
    0.07
    �
    0.07
    匆匆
    0.07
     Zug
    0.07
    shows
    0.07
     tạm
    0.07
    占据了
    0.07
    卖场
    0.06
    Activations Density 0.001%

    No Known Activations