© 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. 17488
    Prev
    Next
    INDEX
    Explanations

    scores and sets

    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
    ä¹ĥèĩ³
    -0.06
     cab
    -0.06
    çĶ¨éĩı
    -0.05
    ç¦ģåĮº
    -0.05
    odega
    -0.05
    leys
    -0.05
    çĶļèĩ³
    -0.05
     sed
    -0.05
    ÑĮе
    -0.05
    avu
    -0.05
    POSITIVE LOGITS
    çīµ
    0.06
    pis
    0.06
    èĥĢ
    0.06
    ihin
    0.05
    ATEN
    0.05
    èĤļ
    0.05
    幸
    0.05
    latt
    0.05
     Newtown
    0.05
    िà¤ķा
    0.05
    Activations Density 0.003%

    No Known Activations