© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18984
    Prev
    Next
    INDEX
    Explanations

    directory paths

    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
     Phen
    -0.05
    èĥĮæĻ¯çļĦ
    -0.05
    ress
    -0.05
    ī
    -0.05
     Sele
    -0.05
     moment
    -0.04
     those
    -0.04
    <|endoftext|>
    -0.04
     splitter
    -0.04
     me
    -0.04
    POSITIVE LOGITS
    ãģĹãģı
    0.07
    haw
    0.07
    mert
    0.06
     ìĦ±ê²©
    0.06
    наÑĢ
    0.06
    cheme
    0.06
    aide
    0.06
    çĮĽè¿Ľ
    0.06
     ()->
    0.06
    ãģĨãģĪ
    0.06
    Activations Density 0.002%

    No Known Activations