© 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. 19172
    Prev
    Next
    INDEX
    Explanations

    `Unit clears`

    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
    avan
    -0.06
    ä¸Ģ举
    -0.06
    UTH
    -0.06
    ienen
    -0.05
    spor
    -0.05
    SJ
    -0.05
    SH
    -0.05
    该
    -0.05
    aly
    -0.05
    RH
    -0.05
    POSITIVE LOGITS
    ampp
    0.05
    éĽĨåĽ¢æľīéĻIJ责任åħ¬åı¸
    0.05
    atics
    0.05
    possible
    0.05
    å¯¹çĽ¸åħ³
    0.05
    èĩ³å°Ĭ
    0.05
    éļIJéļIJ
    0.05
    ennen
    0.05
    times
    0.05
    ç§ijæĬĢæľīéĻIJ责任åħ¬åı¸
    0.05
    Activations Density 0.213%

    No Known Activations