© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21371
    Prev
    Next
    INDEX
    Explanations

    dead zone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĪĨ许
    -0.08
    anaf
    -0.08
    eriksa
    -0.07
    bedingt
    -0.07
    ç¯ĩä¸ī
    -0.07
    tür
    -0.07
    гада
    -0.07
    anggapi
    -0.07
    louv
    -0.07
    èī²åĪĹ
    -0.07
    POSITIVE LOGITS
    -
    0.07
    *
    0.06
    —
    0.06
    x
    0.06
    0.05
    iz
    0.05
    /
    0.05
    \
    0.05
    ist
    0.05
    ÃŃ
    0.05
    Activations Density 0.002%

    No Known Activations