© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20438
    Prev
    Next
    INDEX
    Explanations

    requires

    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
    ric
    -0.06
    tent
    -0.06
    ee
    -0.06
    latt
    -0.05
    artig
    -0.05
    ikten
    -0.05
    неÑģиÑĤе
    -0.05
    èĪį
    -0.05
     Cabe
    -0.05
    æĤī
    -0.05
    POSITIVE LOGITS
     stan
    0.06
    isons
    0.06
    scopes
    0.06
    容æĺĵå¼ķèµ·
    0.06
    彤
    0.06
    enga
    0.06
    .newArrayList
    0.06
     flank
    0.06
     duo
    0.05
     stamina
    0.05
    Activations Density 0.007%

    No Known Activations