© 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. 19019
    Prev
    Next
    INDEX
    Explanations

    W. is

    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
    stein
    -0.07
    mesh
    -0.06
    oste
    -0.06
    å®ĥ们çļĦ
    -0.06
    ike
    -0.06
    abend
    -0.05
    iai
    -0.05
    å·¥åħ·ç®±
    -0.05
    OLO
    -0.05
    ican
    -0.05
    POSITIVE LOGITS
    s
    0.06
    ongs
    0.06
     ÑģмÑĭ
    0.06
    alla
    0.05
    æıĴ
    0.05
    óx
    0.05
     diap
    0.05
    tava
    0.05
    æģIJ
    0.05
    onar
    0.05
    Activations Density 0.007%

    No Known Activations