© 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. 17406
    Prev
    Next
    INDEX
    Explanations

    description

    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
    åijIJ
    -0.06
    amico
    -0.06
    ัà¸Ļ
    -0.06
    esthesia
    -0.06
    æ³¢åıĬ
    -0.06
     Fuck
    -0.06
    ikk
    -0.06
    butt
    -0.06
    æ®ī
    -0.06
    INIT
    -0.05
    POSITIVE LOGITS
    ivor
    0.05
    ÙĤÙħ
    0.05
     yard
    0.05
    би
    0.05
    ÑģÑĤÑĢе
    0.05
    ovo
    0.05
    ovil
    0.05
     Custom
    0.04
    ä»»æĢ§
    0.04
    ube
    0.04
    Activations Density 0.001%

    No Known Activations