© 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. 61405
    Prev
    Next
    INDEX
    Explanations

    independent of position

    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¸įåĪĨ
    -0.08
    ä¸įå°į
    -0.07
    ByUsername
    -0.07
    å¦Ĥæŀľä¸įèĥ½
    -0.07
    íı¬
    -0.07
    toon
    -0.07
    ä¸įæİ¥åıĹ
    -0.07
    <()>
    -0.06
    ä¸į带
    -0.06
    ä¸į容
    -0.06
    POSITIVE LOGITS
    åıªè¦ģåľ¨
    0.10
    åıªè¦ģæĺ¯
    0.10
    åıªè¦ģä½ł
    0.10
    ä½Ĩåıªè¦ģ
    0.10
    åıªè¦ģ
    0.09
     except
    0.09
    å¤ļä¹Ī
    0.09
    åıªçŁ¥éģĵ
    0.09
     whatsoever
    0.08
    åıªè¦ģæĪij们
    0.08
    Activations Density 0.022%

    No Known Activations