© 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. 17245
    Prev
    Next
    INDEX
    Explanations

    cooking methods

    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
    çļĦé«ĺéĢŁ
    -0.06
    é«ĺéĢŁ
    -0.06
    ç¨ĭ度
    -0.06
    缸å½ĵ
    -0.06
    enance
    -0.06
    urious
    -0.06
    urry
    -0.05
    Owners
    -0.05
    cio
    -0.05
    Ñĥж
    -0.05
    POSITIVE LOGITS
    indra
    0.06
    头åı·
    0.05
    æľĢéļ¾
    0.05
     Sob
    0.05
    icking
    0.05
    IONE
    0.05
     Cri
    0.05
    irim
    0.05
    ض
    0.05
    breaking
    0.05
    Activations Density 0.005%

    No Known Activations