© 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. 68956
    Prev
    Next
    INDEX
    Explanations

    Request

    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
     alcuni
    -0.08
    𝔏
    -0.07
     released
    -0.07
     infinite
    -0.07
     cháy
    -0.07
     algún
    -0.07
    graphic
    -0.07
     inflate
    -0.07
     burnt
    -0.06
     Rp
    -0.06
    POSITIVE LOGITS
     "")↵↵
    0.07
    endencies
    0.07
    刊物
    0.07
    ousand
    0.07
    roperty
    0.07
    ividual
    0.07
    之声
    0.06
    ⓢ
    0.06
     Tig
    0.06
     CAN
    0.06
    Activations Density 0.001%

    No Known Activations