© 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. 21673
    Prev
    Next
    INDEX
    Explanations

    seemed to

    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
    @example
    -0.06
    lak
    -0.06
    имÑĥÑīеÑģÑĤв
    -0.06
    an
    -0.06
    åĵĪåĵĪåĵĪ
    -0.06
    iš
    -0.06
    ez
    -0.06
     Rücks
    -0.05
    lessly
    -0.05
    os
    -0.05
    POSITIVE LOGITS
    fillable
    0.06
    æĶ¹çīĪ
    0.06
    igno
    0.06
    åŃ¦ä¹łä¸Ń
    0.06
    jde
    0.06
     внеÑģен
    0.06
    untr
    0.06
    ãĤĪãģĨãģ«ãģªãĤĭ
    0.06
    otate
    0.06
    structuring
    0.05
    Activations Density 0.002%

    No Known Activations