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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 42661
    Prev
    Next
    INDEX
    Explanations

    trimethoprim-sulfamethoxazole

    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
    שול
    -0.06
     coronavirus
    -0.06
     נדר
    -0.06
     Samp
    -0.06
    รถไฟ
    -0.06
     Freund
    -0.06
    失去
    -0.06
    停下来
    -0.06
     Garner
    -0.06
     leicht
    -0.06
    POSITIVE LOGITS
     Commerce
    0.08
    劓
    0.07
    Interest
    0.07
    )/(
    0.07
    רכי
    0.07
     definitions
    0.07
    促进了
    0.07
    .rawQuery
    0.07
     resultant
    0.07
    -object
    0.07
    Activations Density 0.001%

    No Known Activations