© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9495
    Prev
    Next
    INDEX
    Explanations

    preparation and material

    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
    -0.10
    天涯
    -0.10
    uem
    -0.09
    èĭķ
    -0.09
    ingly
    -0.09
    ey
    -0.09
    çĤ³
    -0.08
    perms
    -0.08
    è¯Ħå§Ķ
    -0.08
    ãĤĪãģĨãģª
    -0.08
    POSITIVE LOGITS
    centage
    0.09
    nik
    0.09
    ickle
    0.09
    è§Ī
    0.09
    è®´
    0.08
    done
    0.08
    izon
    0.08
    çľĭ好
    0.08
    çģ£
    0.08
    綦
    0.08
    Activations Density 0.025%

    No Known Activations