© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22280
    Prev
    Next
    INDEX
    Explanations

    ending with noun modifiers

    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
    å·¡
    -0.05
    御åı²
    -0.05
    /
    -0.05
     estim
    -0.05
    [
    -0.05
    aro
    -0.05
    éĩı
    -0.05
    (
    -0.05
    ä¾Ľ
    -0.05
    *
    -0.04
    POSITIVE LOGITS
    fare
    0.07
    maid
    0.06
    atine
    0.06
    æĥĬéŃĤ
    0.06
    imina
    0.06
    ackle
    0.06
    ubber
    0.06
    бÑĥдÑĮÑĤе
    0.06
     crim
    0.06
    REDIS
    0.06
    Activations Density 0.060%

    No Known Activations