© 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. 19154
    Prev
    Next
    INDEX
    Explanations

    the [noun]

    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
    hack
    -0.05
    /\
    -0.05
    udios
    -0.05
    æīĵåŃĶ
    -0.05
     Burgess
    -0.05
    次
    -0.05
     quanto
    -0.05
    won
    -0.05
     Tang
    -0.05
    ctor
    -0.05
    POSITIVE LOGITS
    inge
    0.06
    óf
    0.06
    orate
    0.06
    绪
    0.06
    elts
    0.06
    æİĸ
    0.06
     esp
    0.06
     flu
    0.06
    @admin
    0.05
    à¸Ńà¸ĩ
    0.05
    Activations Density 0.009%

    No Known Activations