© 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. 58896
    Prev
    Next
    INDEX
    Explanations

    climate change alarm

    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
    æĸ°åŁİ
    -0.11
    禧
    -0.10
    èĤļ
    -0.10
    大çĪ·
    -0.09
    çŃ¹å¤ĩ
    -0.09
    é²ľ
    -0.09
    éĥ½åĸľæ¬¢
    -0.09
    åĪĽæĸ°èĥ½åĬĽ
    -0.08
    èĥ¡åŃIJ
    -0.08
    ä¸Ĭå¸Ĥ
    -0.08
    POSITIVE LOGITS
    紧迫
    0.11
    大äºİ
    0.09
    ISTA
    0.09
     urgency
    0.08
    ismo
    0.08
    ista
    0.08
    ERO
    0.08
    çĻ¾å¹´
    0.08
    STA
    0.08
    忧
    0.08
    Activations Density 0.026%

    No Known Activations