© 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. 22255
    Prev
    Next
    INDEX
    Explanations

    hardware specifications

    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
    vis
    -0.06
    bern
    -0.05
    åĢŁåĬ©
    -0.05
     tempo
    -0.05
    bem
    -0.05
    éľĢè¦ģä¸Ģ个
    -0.05
    è´Łèį·
    -0.04
     man
    -0.04
     stage
    -0.04
    æĹ¥æ¶Īæģ¯
    -0.04
    POSITIVE LOGITS
    omie
    0.07
    odaw
    0.07
    isas
    0.07
    ä¸įæį¢
    0.06
    oÄį
    0.06
    YZ
    0.06
    ipu
    0.06
    å¢ŀéĩı
    0.06
     déch
    0.06
    usus
    0.06
    Activations Density 0.020%

    No Known Activations