© 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. 57565
    Prev
    Next
    INDEX
    Explanations

    activity and movement disorders

    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
    ç¥ī
    -0.08
     Wich
    -0.07
    qed
    -0.07
    ä¸Ģç¬Ķ
    -0.07
    çĹĽå¿«
    -0.07
    ceipt
    -0.06
    èī°è¾Ľ
    -0.06
    uters
    -0.06
    æµģè¡Ģ
    -0.06
    दार
    -0.06
    POSITIVE LOGITS
    å¦Ħ
    0.09
    ä¸į稳
    0.09
    ä¸įå®ī
    0.09
     instability
    0.08
    èºģ
    0.08
    失æݧ
    0.08
     unchecked
    0.08
    åĨįèµ·
    0.08
    æī°
    0.08
     unsupported
    0.08
    Activations Density 0.001%

    No Known Activations