© 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. 19-RESID-POST-AA
    6. 75748
    Prev
    Next
    INDEX
    Explanations

    disclaimer

    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
    CHECK
    -0.07
    fício
    -0.07
     act
    -0.07
    הפכה
    -0.07
     collage
    -0.07
    uncio
    -0.07
    under
    -0.07
    captures
    -0.07
    맟
    -0.07
    Beginning
    -0.06
    POSITIVE LOGITS
    portlet
    0.07
     sexy
    0.07
    although
    0.07
     caval
    0.07
    (btn
    0.07
    膝盖
    0.07
    忐
    0.07
    里面的
    0.07
     skept
    0.06
     getArguments
    0.06
    Activations Density 0.000%

    No Known Activations