© 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. 61556
    Prev
    Next
    INDEX
    Explanations

    partial or full

    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
    ä¸įè¿ľ
    -0.09
    绾ç»İ
    -0.08
     ÑģÑĥв
    -0.08
    abbo
    -0.08
    etje
    -0.08
    áĥĶáĥłáĥĺ
    -0.08
    ä»»ä½ķè´¹çĶ¨
    -0.08
    çĸ¾çĹħé¢Ħéĺ²
    -0.08
    elop
    -0.08
    olfo
    -0.08
    POSITIVE LOGITS
    ëĤĺë§Ī
    0.11
    æĪĸéĥ¨åĪĨ
    0.11
    /full
    0.10
    åĴĮéĥ¨åĪĨ
    0.09
     or
    0.08
    æĪĸä¸į
    0.08
    ìĶ©
    0.08
    /part
    0.08
    ä¸įèĥ½å®Įåħ¨
    0.08
    룬
    0.08
    Activations Density 0.079%

    No Known Activations