© 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. 22856
    Prev
    Next
    INDEX
    Explanations

    Hunton, human, HuGene, HuIFN

    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
    åĪ¤
    -0.10
    imir
    -0.10
    finder
    -0.10
    çİĭåŃIJ
    -0.09
    ãģĩ
    -0.09
     McCabe
    -0.08
    èĥĻ
    -0.08
     lÆ°ng
    -0.08
    gang
    -0.08
    ein
    -0.08
    POSITIVE LOGITS
    opot
    0.10
    itor
    0.09
    íĪ¬
    0.09
    ITOR
    0.09
    èĥ¸åīį
    0.09
    pot
    0.09
    è½»æĺĵ
    0.09
    å°ıå°ıçļĦ
    0.08
    itori
    0.08
    arium
    0.08
    Activations Density 0.012%

    No Known Activations