© 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. 1106
    Prev
    Next
    INDEX
    Explanations

    causing harm or negative effects

    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
    æµģæ°ĵ
    -0.09
    åħĪè¿Ľ
    -0.09
    çī¡
    -0.09
    ä¸į失
    -0.09
    é«ĺå±Ĥ次
    -0.09
    _INST
    -0.08
    [method
    -0.08
    å¹´éĻIJ
    -0.08
    é«ĺæ¡£
    -0.08
    庶
    -0.08
    POSITIVE LOGITS
    伤害
    0.13
    åħ³çĪ±
    0.11
    æįŁå®³
    0.10
    累累
    0.10
     harm
    0.10
    rette
    0.10
     Hurt
    0.10
    æĹłæĦı
    0.10
     cruel
    0.10
     Harm
    0.10
    Activations Density 0.033%

    No Known Activations