© 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. 42678
    Prev
    Next
    INDEX
    Explanations

    for its

    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
    ţe
    -0.08
    设å¤ĩè¿Ľè¡Į
    -0.08
    icientes
    -0.07
    /exp
    -0.07
    lesh
    -0.07
    ç¦Ħ
    -0.07
    çļĦ主æµģ
    -0.07
    Ñħий
    -0.07
    ipl
    -0.07
    çļĦä¸ĢåIJį
    -0.07
    POSITIVE LOGITS
     its
    0.15
    åħ¶å¯¹
    0.14
    å®ĥçļĦ
    0.14
    å®ĥéĤ£
    0.12
    åħ¶åľ¨
    0.12
    åħ¶
    0.12
     Its
    0.11
    its
    0.11
     ability
    0.11
    Its
    0.10
    Activations Density 0.423%

    No Known Activations