© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19619
    Prev
    Next
    INDEX
    Explanations

    wrongful death, dismissal, tort

    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
    åıĹ
    -0.09
    tle
    -0.09
    lain
    -0.09
    noon
    -0.08
    ä¸įåĩĨ
    -0.08
    åıĪ被
    -0.08
    .hasClass
    -0.08
    åŃ°
    -0.08
    工夫
    -0.08
    åĬŁå¤«
    -0.08
    POSITIVE LOGITS
    fully
    0.11
    çĤ³
    0.10
    å©¿
    0.10
    åĤ¬çĶŁ
    0.10
    è®·
    0.09
    itas
    0.09
    åĩºæīĭ
    0.09
    åĿĿ
    0.09
    åIJ²
    0.09
    äº
    0.08
    Activations Density 0.006%

    No Known Activations