© 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. 18970
    Prev
    Next
    INDEX
    Explanations

    box shading

    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
    å±ı
    -0.07
    imed
    -0.06
    omotor
    -0.06
    ðŁĻĤ
    -0.05
    çŃĭ
    -0.05
    à¸ķิ
    -0.05
    edom
    -0.05
    è¾ij
    -0.05
    çĽ²
    -0.05
    -screen
    -0.05
    POSITIVE LOGITS
    对èĩªèº«
    0.06
    çĪ±æĥľ
    0.06
     Own
    0.05
    è·Łèĩªå·±
    0.05
    å¯Ĩäºij
    0.05
     /\.(
    0.05
    reuse
    0.05
    ounds
    0.05
     loudly
    0.05
    äºĨ解èĩªå·±çļĦ
    0.05
    Activations Density 0.004%

    No Known Activations