© 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. 47052
    Prev
    Next
    INDEX
    Explanations

    describing measurements

    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
    ǫ
    -0.08
     stun
    -0.08
    Hum
    -0.07
     petite
    -0.07
    占据了
    -0.07
    zone
    -0.07
    뷸
    -0.06
     kle
    -0.06
     gc
    -0.06
    茄
    -0.06
    POSITIVE LOGITS
     retries
    0.08
    DITION
    0.07
    .setLayoutParams
    0.07
    _ISS
    0.07
    PEnd
    0.07
    冼
    0.07
    _MANAGER
    0.07
     seriously
    0.07
     말씀
    0.07
     previous
    0.07
    Activations Density 0.118%

    No Known Activations