© 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. 20757
    Prev
    Next
    INDEX
    Explanations

    invites questions or contests

    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
    æºĸ
    -0.07
    åĩĨ
    -0.07
    heimer
    -0.07
    ÙĦز
    -0.06
    arani
    -0.06
    tene
    -0.06
    qués
    -0.06
    ãĤ»ãĥ¬
    -0.06
    ÃŃv
    -0.06
    ÑĢÑıн
    -0.06
    POSITIVE LOGITS
     ensuing
    0.05
    syl
    0.05
    åĪĨä¹ĭ
    0.04
    atus
    0.04
    acio
    0.04
    W
    0.04
    -
    0.04
     ÑĢазÑĭ
    0.04
    å²IJ
    0.04
     considerable
    0.04
    Activations Density 0.008%

    No Known Activations