© 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. 58279
    Prev
    Next
    INDEX
    Explanations

    eels

    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
    è¯Ĩ
    -0.09
    éĽģ
    -0.09
    åİĭåĪ¶
    -0.08
    ello
    -0.08
    åħįè´£
    -0.08
    åħįéĻ¤
    -0.08
    æ´¾
    -0.08
    è®°å¾Ĺ
    -0.08
    owa
    -0.08
    pad
    -0.08
    POSITIVE LOGITS
    æķħ乡
    0.10
    éĺ´
    0.09
    è°ķ
    0.09
    imbus
    0.08
    otal
    0.08
    åĿij
    0.08
    FIT
    0.08
    鲡
    0.08
    åĬ©
    0.08
    åĿĩåı¯
    0.08
    Activations Density 0.213%

    No Known Activations