© 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. 19337
    Prev
    Next
    INDEX
    Explanations

    prevention of

    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
    (s
    -0.06
     sou
    -0.06
    æļĤ
    -0.05
     (
    -0.05
    éĥģ
    -0.05
     «
    -0.05
    po
    -0.05
    騰
    -0.05
    åħĢ
    -0.05
     po
    -0.05
    POSITIVE LOGITS
    aturahmi
    0.07
    incid
    0.07
    =cv
    0.07
    LOTS
    0.07
    ezo
    0.07
    Hdr
    0.06
    mens
    0.06
    czeÅĽ
    0.06
    Performed
    0.06
    éģĭæ°£
    0.06
    Activations Density 0.037%

    No Known Activations