© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50809
    Prev
    Next
    INDEX
    Explanations

    harm and mistreatment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĩªé¦ĸ
    -0.07
    çłĶåĪ¤
    -0.07
    åħħè£ķ
    -0.07
     catch
    -0.06
    uess
    -0.06
     ìŀ¡
    -0.06
     Explos
    -0.06
    Catch
    -0.06
    catch
    -0.06
    ä¸ĢåĬ¨
    -0.06
    POSITIVE LOGITS
    迫害
    0.12
     perpetrated
    0.12
    èĻIJå¾ħ
    0.11
    åİĭè¿«
    0.11
    åİĭ榨
    0.11
    侵害
    0.10
     merciless
    0.10
    ä¸įåħ¬
    0.10
     oppression
    0.10
    对å¾ħ
    0.10
    Activations Density 0.208%

    No Known Activations