© 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. 1975
    Prev
    Next
    INDEX
    Explanations

    awkwardness and discomfort

    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
    ç²¾ç¥ŀæĸĩæĺİ
    -0.09
    åıijæī¬
    -0.09
    weep
    -0.09
    _variation
    -0.09
    mits
    -0.09
    ves
    -0.08
    ÙĪÙĩ
    -0.08
    uem
    -0.08
    von
    -0.08
    ä¸įåħį
    -0.08
    POSITIVE LOGITS
    ness
    0.18
    ly
    0.16
    å°´å°¬
    0.12
     awkward
    0.12
    NESS
    0.11
    íķĺê²Į
    0.10
    å°´
    0.10
    å±ĢéĿ¢
    0.10
    lic
    0.10
    缸å¤Ħ
    0.10
    Activations Density 0.006%

    No Known Activations