© 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. 32799
    Prev
    Next
    INDEX
    Explanations

    this error

    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
    MES
    -0.09
     pitched
    -0.09
    秫
    -0.09
    åµ´
    -0.08
    PropertyParams
    -0.08
    èIJ½åľ¨
    -0.08
    çĶ¬
    -0.08
    RetVal
    -0.08
    å¿ħ
    -0.08
    ä¸įåIJĪæł¼
    -0.08
    POSITIVE LOGITS
    å¦Ĥä¸ĭ
    0.10
    以ä¸ĭ
    0.10
    ðŁijĩ
    0.09
     below
    0.09
    æĺ¯æ¯Ķè¾ĥ
    0.09
    below
    0.09
     ниже
    0.09
    ä¸ĭåĪĹ
    0.09
    ç»·
    0.09
     following
    0.09
    Activations Density 0.409%

    No Known Activations