© 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. 15-RESID-POST-AA
    11. 49894
    Prev
    Next
    INDEX
    Explanations

    Contrasting statements

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    将会
    -0.07
     comics
    -0.07
     SqlConnection
    -0.07
    шиб
    -0.07
    -powered
    -0.07
    会不会
    -0.07
     assessing
    -0.07
     yeah
    -0.07
    钩
    -0.06
    -button
    -0.06
    POSITIVE LOGITS
    =target
    0.07
    مضي
    0.07
     flipped
    0.07
    璟
    0.07
    腑
    0.06
    を見て
    0.06
    יפ
    0.06
    禄
    0.06
    世俗
    0.06
    (table
    0.06
    Activations Density 0.201%

    No Known Activations