© 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. 19150
    Prev
    Next
    INDEX
    Explanations

    Note that

    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
    X
    -0.05
     X
    -0.05
    w
    -0.05
     agency
    -0.04
     me
    -0.04
    å®ŀå¹²
    -0.04
    nya
    -0.04
    ç«ŀäºīæ¿ĢçĥĪ
    -0.04
    åĽ´ç»ķ
    -0.04
    çļĦ大
    -0.04
    POSITIVE LOGITS
    ucar
    0.07
    ìĤ°
    0.07
    <![
    0.07
    atu
    0.06
    eroy
    0.06
    äºİä»Ĭå¹´
    0.06
    åħĭ森
    0.06
    éĩı
    0.06
     Incre
    0.06
    imate
    0.06
    Activations Density 0.028%

    No Known Activations