© 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. 80510
    Prev
    Next
    INDEX
    Explanations

    negative statements

    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
    Negative Logits
     offsetX
    -0.07
    _HP
    -0.07
    小女孩
    -0.07
     sailors
    -0.07
     protobuf
    -0.06
    气味
    -0.06
    ときに
    -0.06
     restarting
    -0.06
     Helen
    -0.06
    伤病
    -0.06
    POSITIVE LOGITS
    lio
    0.08
    决定
    0.08
    低头
    0.07
    änd
    0.07
    mort
    0.07
     throne
    0.07
     Arc
    0.07
    身创造
    0.07
    _gradient
    0.07
    astered
    0.06
    Activations Density 0.109%

    No Known Activations