© 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. 17947
    Prev
    Next
    INDEX
    Explanations

    as certain phrases or words

    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
    è¢
    -0.06
    akup
    -0.05
    ä¹ħ
    -0.05
    ize
    -0.05
     maxim
    -0.05
    azio
    -0.05
    add
    -0.05
    up
    -0.05
    èĻ½æľī
    -0.05
    åIJĪä½ľçļĦ
    -0.05
    POSITIVE LOGITS
    ernes
    0.07
     meis
    0.07
    lio
    0.06
    kah
    0.06
    eps
    0.06
    ivin
    0.06
    apes
    0.06
    ivals
    0.06
    为åħ¶
    0.06
    OBO
    0.06
    Activations Density 0.020%

    No Known Activations