© 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. 48010
    Prev
    Next
    INDEX
    Explanations

    refereeing and penalties

    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
    足çIJĥéĺŁ
    -0.08
     outputs
    -0.08
    outputs
    -0.07
    åĩºåı£çļĦ
    -0.07
    ä¸į强
    -0.07
    çķħéĶĢ
    -0.07
    fits
    -0.07
     {?
    -0.07
     Outputs
    -0.07
    rapper
    -0.07
    POSITIVE LOGITS
    è§ĦåĪĻ
    0.12
     rules
    0.11
    rules
    0.11
     rulings
    0.10
    è¦ıåīĩ
    0.10
     penalties
    0.10
    Rules
    0.10
    çļĦè§ĦåĪĻ
    0.10
    /rules
    0.10
    è§ĦåĪĻçļĦ
    0.09
    Activations Density 0.083%

    No Known Activations