© 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. 19-RESID-POST-AA
    11. 42048
    Prev
    Next
    INDEX
    Explanations

    file paths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    isto
    -0.07
     exchange
    -0.07
    �
    -0.07
     stranded
    -0.07
    ࠓ
    -0.07
    ﭴ
    -0.07
    3
    -0.07
     British
    -0.07
     liquids
    -0.07
    grund
    -0.06
    POSITIVE LOGITS
    控制系统
    0.07
     wax
    0.07
    _normalize
    0.07
    된
    0.07
     שחור
    0.07
     fung
    0.07
     Chlor
    0.07
    ология
    0.07
     Destructor
    0.07
     bzw
    0.07
    Activations Density 0.002%

    No Known Activations