© 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. 21412
    Prev
    Next
    INDEX
    Explanations

    . followed by something

    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
    æ±ĩéĽĨ
    -0.06
    ilty
    -0.06
    iat
    -0.06
     berbel
    -0.05
    ulo
    -0.05
     happening
    -0.05
    ä½Ĩæĺ¯æ²¡æľī
    -0.05
     campaigned
    -0.05
    æ±ĩéĽĨäºĨ
    -0.05
     adgang
    -0.05
    POSITIVE LOGITS
    angguan
    0.05
    éĻ¡
    0.05
    comings
    0.05
    è¶ĬãģĹ
    0.05
    opan
    0.05
    éĻIJ
    0.05
    æĥ
    0.05
    èĩªå·±æĥ³
    0.05
    ABIL
    0.05
    _exports
    0.05
    Activations Density 0.004%

    No Known Activations