© 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. 21301
    Prev
    Next
    INDEX
    Explanations

    http status codes

    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
    zza
    -0.06
    bbb
    -0.06
    è¦ģåĬłå¤§
    -0.06
    èĨ³
    -0.06
    åħĭåĬĽ
    -0.06
    weisen
    -0.05
    place
    -0.05
    ruh
    -0.05
     claro
    -0.05
    кÑĥпа
    -0.05
    POSITIVE LOGITS
    seh
    0.06
    din
    0.06
    ach
    0.06
    incar
    0.06
    dach
    0.05
     Zut
    0.05
    езд
    0.05
    æī«ä¸Ģæī«
    0.05
    dehy
    0.05
    éªĦ
    0.05
    Activations Density 0.007%

    No Known Activations