© 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. 59512
    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
     RIP
    -0.08
     salopes
    -0.08
     slopes
    -0.07
    lings
    -0.07
    .Hide
    -0.07
     adrenaline
    -0.07
    澄
    -0.07
     ISIS
    -0.07
     טיפול
    -0.07
    _network
    -0.07
    POSITIVE LOGITS
     składa
    0.07
     يكن
    0.07
    蹢
    0.07
     zwłas
    0.07
    toEqual
    0.07
    كان
    0.07
    そんな
    0.06
     وكانت
    0.06
    轪
    0.06
    uyo
    0.06
    Activations Density 0.550%

    No Known Activations