© 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 EvalsExportsAPI 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. 83768
    Prev
    Next
    INDEX
    Explanations

    Acinetobacter and negative results

    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
    Not in Any Lists

    No Comments

    Negative Logits
    שהו
    -0.08
     ничего
    -0.07
     Yük
    -0.07
     תלוי
    -0.07
    El
    -0.07
     mientras
    -0.07
    嵫
    -0.07
    חוף
    -0.07
    ODO
    -0.07
     protagonists
    -0.07
    POSITIVE LOGITS
    卫
    0.07
    shal
    0.06
    foundation
    0.06
    big
    0.06
    *(
    0.06
    MISSION
    0.06
    BIT
    0.06
    ickle
    0.06
    _texts
    0.06
    ัด
    0.06
    Activations Density 0.001%

    No Known Activations