© 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. 3643
    Prev
    Next
    INDEX
    Explanations

    negative outcomes or situations

    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
    åħī彩
    -0.10
    ikki
    -0.09
    allis
    -0.09
    åĩ¶
    -0.09
    obar
    -0.09
     Pir
    -0.09
    åıijéħµ
    -0.09
    仪
    -0.09
    åľĨ
    -0.08
    forth
    -0.08
    POSITIVE LOGITS
    å¼±åĬ¿
    0.09
    è¾ľè´Ł
    0.09
    鹫
    0.09
    è¨Ĺ
    0.09
     sadd
    0.09
    æłĹ
    0.09
    åĿij
    0.09
    æĭĸ
    0.08
    èĤ¡
    0.08
    被éªĹ
    0.08
    Activations Density 0.062%

    No Known Activations