© 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. 70347
    Prev
    Next
    INDEX
    Explanations

    breed

    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
     yal
    -0.07
     at
    -0.06
     dbus
    -0.06
    ᴖ
    -0.06
     alcan
    -0.06
     дан
    -0.06
     mux
    -0.06
     présente
    -0.06
     cuốn
    -0.06
    Vec
    -0.06
    POSITIVE LOGITS
    addle
    0.07
    _verify
    0.07
    [train
    0.07
    だろう
    0.07
    谕
    0.07
    indle
    0.07
    _tim
    0.07
     скорость
    0.07
    Noise
    0.07
    ursors
    0.07
    Activations Density 0.001%

    No Known Activations