© 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. 2343
    Prev
    Next
    INDEX
    Explanations

    likelihood, possibility, feasibility

    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
    缯
    -0.10
    aura
    -0.09
    _ipc
    -0.09
    ä¸Ģå¤Ħ
    -0.09
    ç§ĺå¯Ĩ
    -0.08
    è°´
    -0.08
    åģ¥
    -0.08
    ç¼İ
    -0.08
    使人
    -0.08
     tremendous
    -0.08
    POSITIVE LOGITS
    çļĦåı¯èĥ½æĢ§
    0.12
    ãĤ®ãĥ£
    0.10
    è¿«ä¸įåıĬå¾ħ
    0.09
     forthcoming
    0.09
    éħĿéħ¿
    0.09
    åı¯èĥ½æĢ§
    0.09
    éĴ»çłĶ
    0.09
     possibility
    0.09
    åĨ·åį´
    0.08
    ä¸İåIJ¦
    0.08
    Activations Density 0.179%

    No Known Activations