© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46642
    Prev
    Next
    INDEX
    Explanations

    doesn't or list separators

    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
    ç´Ģ
    -0.07
    alph
    -0.07
    å¿ĥæĤ¦
    -0.07
    etro
    -0.07
    åĪĩ
    -0.07
    ihal
    -0.07
    ihak
    -0.06
    lej
    -0.06
    使å®ĥ
    -0.06
    åĪ©
    -0.06
    POSITIVE LOGITS
    åIJĮä¸Ĭ
    0.07
    alas
    0.07
    länd
    0.07
    èĻ½çĦ¶æľī
    0.07
    è¦ģç´ł
    0.07
    éĢĹ
    0.06
    oskop
    0.06
    æ¸ħåįİ
    0.06
    اة
    0.06
    åı¯æĥ³
    0.06
    Activations Density 0.001%

    No Known Activations