© 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. 24069
    Prev
    Next
    INDEX
    Explanations

    scrubbers, traps, filters, dust collection

    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
    crow
    -0.08
    áĥĶáĥ¢
    -0.07
    OwnProperty
    -0.07
     crow
    -0.07
    irut
    -0.07
    @Entity
    -0.07
     Dorm
    -0.07
     Widodo
    -0.07
    ä¸İåIJĪä½ľ
    -0.07
    ahuan
    -0.07
    POSITIVE LOGITS
    /filter
    0.11
     filter
    0.10
    è¿ĩ滤
    0.10
    å°¾æ°Ķ
    0.09
     filtr
    0.09
     filtration
    0.09
     filters
    0.09
    filters
    0.09
    è£ħæľī
    0.08
    filter
    0.08
    Activations Density 0.013%

    No Known Activations