© 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. 49274
    Prev
    Next
    INDEX
    Explanations

    Dean or Hammond

    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
    ILING
    -0.10
    æIJ´
    -0.09
    åıijéŁ³
    -0.09
    سÙģ
    -0.09
     Garner
    -0.09
    æľºåŀĭ
    -0.09
    ứng
    -0.09
    æĺ¯æľĢ
    -0.09
    Parm
    -0.09
    çı¥
    -0.08
    POSITIVE LOGITS
    çħ¤çŁ¿
    0.15
    çħ¤
    0.14
    çħ¤çĤŃ
    0.14
    Coal
    0.13
     coal
    0.12
     Coal
    0.12
    coal
    0.10
    æİĺ
    0.10
    åĨ¶éĩij
    0.10
    磸
    0.10
    Activations Density 0.238%

    No Known Activations