© 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. 18379
    Prev
    Next
    INDEX
    Explanations

    network, text, entity, function, data

    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
    马
    -0.06
    éĶĻè¿ĩ
    -0.06
    eli
    -0.06
    ä¿©
    -0.06
    è¯ķ
    -0.05
    ìĿ´ëĭ¤
    -0.05
    heil
    -0.05
    нÑĭ
    -0.05
    ازÙĦ
    -0.05
    ponsored
    -0.05
    POSITIVE LOGITS
     ÙĪØ¥ÙĦÙī
    0.05
    apta
    0.05
    å±ħ
    0.05
    çĦ¶åIJİå°±
    0.05
    chein
    0.05
    usher
    0.05
    veld
    0.05
    oyer
    0.05
    rimi
    0.05
    pressive
    0.05
    Activations Density 0.143%

    No Known Activations