© 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. 21068
    Prev
    Next
    INDEX
    Explanations

    managing digital communications

    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
    itty
    -0.07
    horn
    -0.06
    zier
    -0.06
    ogan
    -0.06
    èm
    -0.06
    ignal
    -0.06
    åİŁä½ľèĢħ
    -0.06
    ultz
    -0.06
    каÑĤÑĮ
    -0.06
    æ¨
    -0.06
    POSITIVE LOGITS
    ago
    0.06
     busiest
    0.05
    elijkse
    0.05
    à¹Ģหล
    0.05
    åĪĨå¸ĥ
    0.05
    æ¶Ł
    0.05
    对åĨħ
    0.05
     Æ°á»Ľc
    0.05
     Princip
    0.05
     tü
    0.05
    Activations Density 0.036%

    No Known Activations