© 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. 20442
    Prev
    Next
    INDEX
    Explanations

    moving on or forward

    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
    andard
    -0.06
    wyn
    -0.06
    使çĶ¨æĸ¹æ³ķ
    -0.06
    endance
    -0.06
    ä¸įä¸ĭ
    -0.06
    éĥijéĩį声æĺİ
    -0.05
    ween
    -0.05
    ä¸Ģ次
    -0.05
    »
    -0.05
    éħįåIJĪ
    -0.05
    POSITIVE LOGITS
    ivos
    0.06
    ernaut
    0.05
    辦
    0.05
    dere
    0.05
    ä½įæķ°
    0.05
    ivas
    0.05
    torch
    0.05
    idão
    0.05
    çĴIJ
    0.05
    ؤ
    0.05
    Activations Density 0.003%

    No Known Activations