© 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. 18798
    Prev
    Next
    INDEX
    Explanations

    malloc, struct, C code

    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
    å¸ľ
    -0.08
     PED
    -0.08
    èĪIJ
    -0.08
    享
    -0.08
     organ
    -0.08
     ig
    -0.08
    \<^
    -0.07
    ä¸įæľį
    -0.07
     Trib
    -0.07
    oli
    -0.07
    POSITIVE LOGITS
    =NULL
    0.11
     NULL
    0.10
    Malloc
    0.09
    _errno
    0.09
    (NULL
    0.09
    ,NULL
    0.09
    å¼łå®¶
    0.08
     malloc
    0.08
    å®ı
    0.08
    èľĪ
    0.08
    Activations Density 1.297%

    No Known Activations