© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17921
    Prev
    Next
    INDEX
    Explanations

    rounds, games, blocks, units

    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
    ä¸ŃåĽ½å®¶
    -0.06
    ä¸Ģå¸Ĩ
    -0.06
     деклаÑĢаÑĨии
    -0.06
    isman
    -0.06
    çŃīåĽ½å®¶
    -0.06
    arele
    -0.06
    ãĤıãĤĬãģ«
    -0.06
    etre
    -0.05
    asang
    -0.05
    NST
    -0.05
    POSITIVE LOGITS
    mer
    0.06
    they
    0.05
    const
    0.05
     cease
    0.05
    axy
    0.05
    comm
    0.05
     Äĵ
    0.05
    åº
    0.05
    ัà¸ģ
    0.05
    tero
    0.05
    Activations Density 0.002%

    No Known Activations