© 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. 47982
    Prev
    Next
    INDEX
    Explanations

    exception types and code identifiers

    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
    æĢ§åľ°
    -0.08
    ized
    -0.08
    请èģĶç³»åĪłéĻ¤
    -0.08
    åĮĸåıijå±ķ
    -0.08
    istic
    -0.08
    äºĮåŃĹ
    -0.07
    èµ·è§ģ
    -0.07
    rnd
    -0.07
    обо
    -0.07
    ization
    -0.07
    POSITIVE LOGITS
    度çļĦ
    0.07
    halts
    0.07
    olumes
    0.07
    oller
    0.07
    akes
    0.07
    ми
    0.07
    оÑĢо
    0.07
    igenschaften
    0.07
    å§Ķ书记
    0.07
    kel
    0.07
    Activations Density 0.225%

    No Known Activations