© 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. 5424
    Prev
    Next
    INDEX
    Explanations

    ̀

    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
    Design
    -0.08
     Alison
    -0.08
    Lead
    -0.08
    기업
    -0.07
    揣
    -0.07
    enis
    -0.07
    .Design
    -0.07
    大胆
    -0.07
    operate
    -0.07
     Up
    -0.07
    POSITIVE LOGITS
     Apost
    0.07
     Jahr
    0.07
     nymph
    0.07
    江门
    0.07
     Zhou
    0.06
     מזה
    0.06
     kata
    0.06
    �
    0.06
     RFC
    0.06
     indications
    0.06
    Activations Density 0.119%

    No Known Activations