© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RESID-POST-AA
    11. 57800
    Prev
    Next
    INDEX
    Explanations

    handle

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ($(
    -0.08
    一起来
    -0.07
    (enable
    -0.07
    ậ
    -0.07
    奔赴
    -0.07
    alış
    -0.07
     mama
    -0.07
     ($(
    -0.07
    бер
    -0.07
    护卫
    -0.06
    POSITIVE LOGITS
    	Connection
    0.07
    syn
    0.07
     sampled
    0.07
    招聘会
    0.07
    projection
    0.07
    员
    0.07
    的社会
    0.06
    샏
    0.06
    .characters
    0.06
    Socket
    0.06
    Activations Density 0.051%

    No Known Activations