© 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. 21466
    Prev
    Next
    INDEX
    Explanations

    STATE of Texas

    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
    elor
    -0.06
    stick
    -0.05
    åħļ
    -0.05
     notific
    -0.05
     bart
    -0.05
    igr
    -0.05
     jong
    -0.05
    çį
    -0.05
    ensi
    -0.05
     vibra
    -0.05
    POSITIVE LOGITS
    .truth
    0.07
    uest
    0.06
    rides
    0.06
     Sayangnya
    0.06
    uar
    0.06
     Byrne
    0.06
    ä¸Ģåı¶
    0.06
    AndGet
    0.05
    æľ«å¹´
    0.05
    reo
    0.05
    Activations Density 0.007%

    No Known Activations