© 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. 17097
    Prev
    Next
    INDEX
    Explanations

    mild, deep, room, equilateral, server, infinite, output

    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
    recken
    -0.06
    reen
    -0.06
    REEN
    -0.06
    pack
    -0.06
    åĩºä¸įç©·
    -0.06
    èĮ§
    -0.05
    antan
    -0.05
     chiá»ģu
    -0.05
    éĢŁ
    -0.05
    Ỽm
    -0.05
    POSITIVE LOGITS
    iol
    0.05
    cid
    0.05
    WS
    0.05
    ime
    0.05
    AME
    0.05
    Ñħе
    0.05
    ass
    0.05
    ame
    0.05
     Variety
    0.05
     Prof
    0.05
    Activations Density 0.026%

    No Known Activations