© 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. 20289
    Prev
    Next
    INDEX
    Explanations

    by or by

    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
    illin
    -0.06
    ipient
    -0.05
    个æķ°
    -0.05
    ondo
    -0.05
     âĦĸ
    -0.05
    ä¼łåªĴæľīéĻIJåħ¬åı¸
    -0.05
    ä¸İå®ŀè·µ
    -0.05
    rique
    -0.04
     plenty
    -0.04
    åľĥ
    -0.04
    POSITIVE LOGITS
    åŃľ
    0.07
    bart
    0.06
    ajor
    0.06
    è®°è´¦
    0.06
    åħ¨æ°ij
    0.06
    anam
    0.06
    yyyyMMdd
    0.06
    inste
    0.06
    ALS
    0.06
    veld
    0.06
    Activations Density 0.004%

    No Known Activations