© 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. 17837
    Prev
    Next
    INDEX
    Explanations

    folding and folds

    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
    ential
    -0.06
    irkan
    -0.06
    irn
    -0.05
    irro
    -0.05
    ward
    -0.05
    matic
    -0.05
    idr
    -0.05
    ecu
    -0.05
    linger
    -0.05
    ¡´
    -0.05
    POSITIVE LOGITS
     Folding
    0.08
     folding
    0.08
     folds
    0.08
     Fold
    0.07
    æĬĺåıł
    0.07
    -fold
    0.07
    .fold
    0.07
    _fold
    0.06
     fold
    0.06
    æĬĺãĤĬ
    0.06
    Activations Density 0.024%

    No Known Activations