© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 27074
    Prev
    Next
    INDEX
    Explanations

    GPS and geographic data files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    èĴĻ
    -0.11
    ä¸įåĬ¨
    -0.11
    .borrow
    -0.10
    éĢıæĺİ
    -0.10
    éĹªçĥģ
    -0.10
    HORT
    -0.09
    è¿Ŀ
    -0.09
    çĥŁ
    -0.09
    æĤłæĤł
    -0.09
    èĨĪ
    -0.09
    POSITIVE LOGITS
    _coverage
    0.10
    è¶Ł
    0.09
    åĬŁè¯¾
    0.09
    æī«
    0.09
     coverage
    0.09
    ä¸Ģéģį
    0.09
    åħ¨è¦ĨçĽĸ
    0.08
    ä¹Łä¸įåı¯èĥ½
    0.08
    owie
    0.08
    owitz
    0.08
    Activations Density 0.093%

    No Known Activations