© 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. 16975
    Prev
    Next
    INDEX
    Explanations

    see if

    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
    imizer
    -0.06
     helst
    -0.06
    μÎŃ
    -0.06
    kaus
    -0.06
    cula
    -0.06
    ÑģловиÑı
    -0.06
    åħĭéĩĮ
    -0.06
    ãģŁãĤī
    -0.05
     ofre
    -0.05
     داش
    -0.05
    POSITIVE LOGITS
    a
    0.08
    warzys
    0.06
    ãģ®ãģ¿
    0.05
    åĽłç´łå½±åĵį
    0.05
    rim
    0.05
    maker
    0.05
    auc
    0.05
    buie
    0.05
    erat
    0.05
    upon
    0.05
    Activations Density 0.011%

    No Known Activations