© 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. 19-RESID-POST-AA
    11. 70169
    Prev
    Next
    INDEX
    Explanations

    would

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    鹅
    -0.07
     крови
    -0.07
     używa
    -0.07
     лучших
    -0.07
    .moveTo
    -0.06
    悪い
    -0.06
     già
    -0.06
    (firstName
    -0.06
     hopeful
    -0.06
    zyć
    -0.06
    POSITIVE LOGITS
     Chun
    0.08
    productName
    0.07
    civil
    0.07
    ┑
    0.07
    헝
    0.07
     cached
    0.06
    Mother
    0.06
     edited
    0.06
    boss
    0.06
    casting
    0.06
    Activations Density 0.000%

    No Known Activations