© 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. 44021
    Prev
    Next
    INDEX
    Explanations

    grouping or sectioning

    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
    езд
    -0.06
    /
    -0.06
    jø
    -0.06
    ht
    -0.06
    ä¹ĭå¹´
    -0.06
    åį´åľ¨
    -0.06
    åıĪåľ¨
    -0.06
    canonical
    -0.06
    anel
    -0.06
    pt
    -0.06
    POSITIVE LOGITS
    ä¸īæĺ¯
    0.08
     inoltre
    0.08
    [--
    0.08
    ä¸ĢæŦåıijçĶŁ
    0.08
    *)"
    0.08
    èĢ³çĨŁèĥ½è¯¦
    0.07
    åģļçļĦäºĭ
    0.07
    ayar
    0.07
    asley
    0.07
    aramente
    0.07
    Activations Density 0.001%

    No Known Activations