© 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. 22141
    Prev
    Next
    INDEX
    Explanations

    points in time or moments

    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°¤åħ¶
    -0.06
    å°ij
    -0.05
    ()
    -0.05
    /
    -0.05
     particularly
    -0.05
    è·¯ä¸Ĭ
    -0.05
    èį¡
    -0.05
    \"
    -0.05
    èĪį
    -0.05
     Wich
    -0.05
    POSITIVE LOGITS
    ibia
    0.07
    æ¯Ķèĩªå·±
    0.07
    rij
    0.07
    åıįæŃ£
    0.07
    è·Łèĩªå·±
    0.06
    erait
    0.06
    åĬłæĭ¿å¤§
    0.06
    OF
    0.06
    éĥ¨å°±
    0.06
    obia
    0.06
    Activations Density 0.005%

    No Known Activations