© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 18490
    Prev
    Next
    INDEX
    Explanations

    -page

    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
    فئة
    -0.07
     gest
    -0.07
     lateral
    -0.07
    ipient
    -0.06
    姓
    -0.06
    幛
    -0.06
    毛泽
    -0.06
    -cultural
    -0.06
     السيد
    -0.06
    企业和
    -0.06
    POSITIVE LOGITS
    PLAY
    0.08
    prove
    0.08
    铲
    0.07
     loggedIn
    0.07
     confused
    0.07
    Online
    0.07
     corrobor
    0.07
     Online
    0.07
    /wiki
    0.06
     Making
    0.06
    Activations Density 0.001%

    No Known Activations