© 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. 17318
    Prev
    Next
    INDEX
    Explanations

    constructor syntax: (

    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
    -0.06
     ...
    -0.06
     d
    -0.06
    ?
    -0.05
     V
    -0.05
    ï¸ı
    -0.05
    ge
    -0.05
     g
    -0.05
     (
    -0.05
     t
    -0.05
    POSITIVE LOGITS
     **.**
    0.07
    Äĥr
    0.07
    aliza
    0.07
    ведением
    0.07
    .FormBorderStyle
    0.07
    classed
    0.07
     Gradu
    0.07
    Ñģме
    0.07
    itched
    0.07
    achable
    0.07
    Activations Density 0.012%

    No Known Activations