© 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. 22136
    Prev
    Next
    INDEX
    Explanations

    diversity, dish, Cars, findings, trace, implications, bug, same, key, form

    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
     vs
    -0.06
    æĤ¨å°±åı¯ä»¥
    -0.06
     versus
    -0.05
    ice
    -0.05
    -wise
    -0.05
    以ä¸ĭåĩłçĤ¹
    -0.05
    yna
    -0.05
    ubit
    -0.05
    ..)
    -0.05
    umpul
    -0.05
    POSITIVE LOGITS
    ogl
    0.06
     bila
    0.06
    endon
    0.06
    ahlen
    0.06
    eringen
    0.06
    zew
    0.05
    anches
    0.05
    端çĿĢ
    0.05
    sver
    0.05
    кÑĢема
    0.05
    Activations Density 0.003%

    No Known Activations