© 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. 31408
    Prev
    Next
    INDEX
    Explanations

    dataset rows of ions

    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
     individuel
    -0.07
    emers
    -0.07
    REEN
    -0.07
    individ
    -0.07
    ä¸ĢçŃī
    -0.07
    ä¸įèĢIJ
    -0.07
    _OVERRIDE
    -0.07
    çŃīèijĹ
    -0.07
    Mul
    -0.07
    è¶ģ
    -0.07
    POSITIVE LOGITS
    åħĪè¡Į
    0.09
    åħĪãģ«
    0.08
    å¿ħé¡»åħĪ
    0.08
    åľ¨åħĪ
    0.07
    åħĪçĶ¨
    0.07
    åı¯ä»¥å¸®åĬ©
    0.07
    åħĪåľ¨
    0.07
    (reference
    0.07
    Äįnosti
    0.07
    åħĪå¾Ĺ
    0.07
    Activations Density 0.380%

    No Known Activations