© 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. 18791
    Prev
    Next
    INDEX
    Explanations

    contact us

    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
    âĢ¦it
    -0.10
    âĢ¦the
    -0.08
    âĢ¦I
    -0.08
    âĢ¦but
    -0.08
    [âĢ¦
    -0.08
     obsta
    -0.08
     [âĢ¦
    -0.08
    bid
    -0.08
    ipot
    -0.08
    åį³åı¯æŁ¥çľĭ
    -0.08
    POSITIVE LOGITS
    éĩı
    0.06
    W
    0.06
    大
    0.06
    "
    0.06
    ä¸į
    0.06
    æī¿
    0.06
    H
    0.06
    /
    0.06
    åı¶
    0.05
    0.05
    Activations Density 0.098%

    No Known Activations