© 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. 11-RESID-POST-AA
    11. 72018
    Prev
    Next
    INDEX
    Explanations

    Proof complexities/size

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Lane
    -0.07
    uish
    -0.07
     markdown
    -0.07
    <|im_start|>
    -0.07
    掘
    -0.06
    —all
    -0.06
    (QL
    -0.06
    -B
    -0.06
    ()},↵
    -0.06
    隰
    -0.06
    POSITIVE LOGITS
    那么多
    0.07
     parked
    0.07
     intersect
    0.07
     Tutor
    0.06
    休み
    0.06
     loạt
    0.06
     Note
    0.06
    =:
    0.06
    _MODULES
    0.06
    ᥔ
    0.06
    Activations Density 0.025%

    No Known Activations