© 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. 17710
    Prev
    Next
    INDEX
    Explanations

    instructions and guidance

    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
    urz
    -0.06
    å§ĵåIJį
    -0.06
    има
    -0.06
    izzer
    -0.06
    ILI
    -0.06
    inish
    -0.06
    æģķ
    -0.05
    ¶
    -0.05
    åĩºå¼µ
    -0.05
    êncio
    -0.05
    POSITIVE LOGITS
    ice
    0.06
    .example
    0.05
    aul
    0.05
    lost
    0.05
    ley
    0.05
    FIG
    0.05
    is
    0.05
    пелÑĮ
    0.05
    handleSubmit
    0.05
    adou
    0.05
    Activations Density 0.016%

    No Known Activations