© 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. 16948
    Prev
    Next
    INDEX
    Explanations

    references to previously mentioned items

    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
    æ¤į
    -0.05
    æ¯Ķå¦Ĥåľ¨
    -0.05
     bib
    -0.05
    've
    -0.05
    å¸ĸ
    -0.05
    uc
    -0.05
    ubby
    -0.05
    ju
    -0.05
    ama
    -0.05
     de
    -0.05
    POSITIVE LOGITS
    arate
    0.07
    صر
    0.07
    alts
    0.07
    ywa
    0.06
    ncy
    0.06
    ermen
    0.06
    lamento
    0.06
    puties
    0.06
    inals
    0.06
    riendly
    0.06
    Activations Density 0.001%

    No Known Activations