© 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. 19761
    Prev
    Next
    INDEX
    Explanations

    type, step, implicit, RFC, Pat, inet, job

    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
    åłĨ
    -0.07
     appunto
    -0.07
    æ±¾
    -0.06
    å¸ĮæľĽå¯¹å¤§å®¶
    -0.06
    å¦Ĥä¸ĭ
    -0.06
    ä¸ĭåIJĮ
    -0.05
    /[
    -0.05
    as
    -0.05
    çĦķ
    -0.05
    çīĩçīĩ
    -0.05
    POSITIVE LOGITS
    åıĪå¦Ĥ
    0.10
     natomiast
    0.10
     ëĺIJíķľ
    0.10
    åĭĩå¾Ģ缴åīį
    0.10
    åIJĮçIJĨ
    0.10
    åħ¬ç½ijå®īå¤ĩ
    0.09
     inoltre
    0.09
     hingegen
    0.09
    åı¦å¤ĸä¸Ģç§į
    0.09
    ä»»ä½ķåħ¶ä»ĸ
    0.09
    Activations Density 0.077%

    No Known Activations