© 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. 16870
    Prev
    Next
    INDEX
    Explanations

    forward movement or direction

    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
    деÑģÑı
    -0.06
    ÑĤ
    -0.06
    chy
    -0.06
    ords
    -0.06
    orts
    -0.06
    ëģĶ
    -0.06
    ê¹IJ
    -0.06
    ê¾¼
    -0.06
     hendak
    -0.06
    SPEC
    -0.06
    POSITIVE LOGITS
    ever
    0.08
    ly
    0.07
    swith
    0.07
    ship
    0.07
    ive
    0.06
    ãĤ¥
    0.06
    ×Ļ×ķ
    0.06
    ãģĹãģıãģ¯
    0.06
    ood
    0.06
    eza
    0.06
    Activations Density 0.017%

    No Known Activations