© 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. 21160
    Prev
    Next
    INDEX
    Explanations

    slot with sand and mice

    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
     allow
    -0.05
    on
    -0.05
    raft
    -0.05
    mey
    -0.05
     allowed
    -0.05
    -complete
    -0.05
     allows
    -0.05
    me
    -0.05
    çļĦè¯Ŀ
    -0.05
    uler
    -0.04
    POSITIVE LOGITS
    andre
    0.07
    inasikan
    0.07
    elah
    0.06
    ergen
    0.06
    æľīæĸ°çļĦ
    0.06
    angstrom
    0.06
    ÙĪار
    0.06
    icznie
    0.06
     Litt
    0.06
    geries
    0.06
    Activations Density 0.084%

    No Known Activations