© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 112041
    Prev
    Next
    INDEX
    Explanations

    death and medical emergencies

    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
    Not in Any Lists

    No Comments

    Negative Logits
    四十
    -0.07
    /comment
    -0.07
    两只
    -0.07
    臆
    -0.07
    疼
    -0.07
     Lips
    -0.07
    的一部分
    -0.07
     Pax
    -0.07
     أفريقي
    -0.07
    𝇊
    -0.06
    POSITIVE LOGITS
     kam
    0.07
    下游
    0.07
    jd
    0.07
    jav
    0.07
    0.07
    𫘦
    0.06
    .showMessageDialog
    0.06
    MainThread
    0.06
    东南亚
    0.06
    =localhost
    0.06
    Activations Density 0.058%

    No Known Activations