© 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. 19326
    Prev
    Next
    INDEX
    Explanations

    speaks so loud

    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
    ç²¾
    -0.06
    :
    -0.05
    âĢĮ
    -0.05
     Ra
    -0.05
     Ga
    -0.05
    -
    -0.05
    ä»ĺ
    -0.05
    ah
    -0.05
     (
    -0.04
    ä½ĵ
    -0.04
    POSITIVE LOGITS
    à¸ļัà¸ĩà¸Ħัà¸ļ
    0.08
    ä½ĻåĬĽ
    0.08
    бÑĢи
    0.07
    gara
    0.07
    çī¹çº§
    0.07
     **¡
    0.07
     ìļķìĭ¤
    0.07
    nahm
    0.07
     retur
    0.07
    çģ«çĥ§
    0.07
    Activations Density 0.014%

    No Known Activations