© 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. 21614
    Prev
    Next
    INDEX
    Explanations

    head of

    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
    æĪ¿åĨħ
    -0.07
    è°İ
    -0.06
    ẩu
    -0.06
    rum
    -0.06
    á»Ļt
    -0.06
    æŀģéĢŁ
    -0.06
    ãĥĥãĤ·ãĥ³ãĤ°
    -0.06
    ivan
    -0.06
    enser
    -0.06
    éģ¥éģ¥
    -0.06
    POSITIVE LOGITS
     pert
    0.05
    è°ĥæķ´
    0.05
    交åıī
    0.05
    ä¿®æŃ£
    0.05
    pa
    0.05
    ter
    0.05
    arine
    0.05
     ter
    0.04
     transition
    0.04
     dov
    0.04
    Activations Density 0.041%

    No Known Activations