© 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. 49533
    Prev
    Next
    INDEX
    Explanations

    cadaver or corpse 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
    èĺ§
    -0.11
    idden
    -0.09
    builtin
    -0.09
    ä¸ĢéĿ¢
    -0.09
    aise
    -0.09
    imon
    -0.08
    IDA
    -0.08
     Sle
    -0.08
     Shepherd
    -0.08
    è¶Ł
    -0.08
    POSITIVE LOGITS
    å°¸ä½ĵ
    0.16
    å±į
    0.14
    å°¸
    0.14
     corpses
    0.11
    å¼ĥ
    0.11
    骨æŀ¶
    0.11
     corpse
    0.11
     carc
    0.10
    éĺ²èħIJ
    0.10
    åºĸ
    0.10
    Activations Density 0.256%

    No Known Activations