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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 61092
    Prev
    Next
    INDEX
    Explanations

    Plotting functions

    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
     Sense
    -0.08
     CUT
    -0.07
    Ự
    -0.07
    太久
    -0.07
    .HOUR
    -0.07
     THINK
    -0.07
    .calls
    -0.07
    LTR
    -0.06
    舞
    -0.06
     Fist
    -0.06
    POSITIVE LOGITS
     agrees
    0.07
    档
    0.07
     kc
    0.07
     iht
    0.07
    ancements
    0.07
    但如果
    0.06
    idences
    0.06
    recipe
    0.06
     barrel
    0.06
    ומי
    0.06
    Activations Density 0.004%

    No Known Activations