© 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. 17279
    Prev
    Next
    INDEX
    Explanations

    back, comparison, online, other

    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
     graças
    -0.06
    less
    -0.06
    anna
    -0.06
    ä¹ĭäºĮ
    -0.06
     اÙĦاÙĪÙĦÙī
    -0.06
    adis
    -0.06
    Ùħرض
    -0.06
    ç¹°ãĤĬè¿Ķ
    -0.06
    дÑĸй
    -0.06
     sacco
    -0.06
    POSITIVE LOGITS
    оÑģÑĤо
    0.06
    pel
    0.05
    ouver
    0.05
    иÑĤелÑĮÑģÑĤво
    0.05
    pend
    0.05
    tor
    0.05
    clair
    0.05
    uten
    0.05
    ucks
    0.05
     Shack
    0.05
    Activations Density 0.011%

    No Known Activations