© 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. 70311
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Negative Logits
     wannonce
    -0.07
    .WinControls
    -0.07
    tığımız
    -0.06
    played
    -0.06
    免除
    -0.06
    بطل
    -0.06
    _recursive
    -0.06
    BUTTON
    -0.06
    يمة
    -0.06
    㭎
    -0.06
    POSITIVE LOGITS
     Warn
    0.08
    爪
    0.07
     quarters
    0.07
     pass
    0.07
    媽
    0.07
    羽毛
    0.07
     Wrap
    0.07
    警察
    0.07
    -ps
    0.06
    む
    0.06
    Activations Density 0.068%

    No Known Activations