© 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. 18068
    Prev
    Next
    INDEX
    Explanations

    learning feedback

    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
    -0.06
    Âł
    -0.06
    ↵
    -0.06
    -
    -0.05
    ~
    -0.05
    anim
    -0.05
    åĬ¨äº§
    -0.05
    ↵↵
    -0.05
    ä¸Ģèµ·
    -0.05
    çł´
    -0.05
    POSITIVE LOGITS
    edback
    0.08
    åĽŀè¿ĩç¥ŀ
    0.07
    afür
    0.07
     voord
    0.07
    æݪ并举
    0.07
    .getMonth
    0.07
     ratus
    0.07
    리íķľ
    0.07
    deaux
    0.07
    æĥ
    0.07
    Activations Density 0.002%

    No Known Activations