© 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. 19361
    Prev
    Next
    INDEX
    Explanations

    API key and calls

    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
    ups
    -0.05
     laku
    -0.05
    arel
    -0.05
     brisk
    -0.05
    orsa
    -0.05
    ustru
    -0.05
    ran
    -0.05
    æīĢåѦ
    -0.05
    ãĥĸãĥ©
    -0.05
    ris
    -0.05
    POSITIVE LOGITS
    Einst
    0.06
     réf
    0.06
     veril
    0.06
    æ»ħ
    0.06
    ayne
    0.06
    PerPixel
    0.06
    damage
    0.06
    Arguments
    0.06
    atively
    0.06
    sten
    0.05
    Activations Density 0.006%

    No Known Activations