© 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. 34813
    Prev
    Next
    INDEX
    Explanations

    Inhal, inge, dal

    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
    abet
    -0.10
    ÐIJÐĹ
    -0.09
    ummer
    -0.09
     legend
    -0.09
    ectomy
    -0.08
    ermo
    -0.08
    gest
    -0.08
    éĢIJ
    -0.08
    æ´Ĺæīĭ
    -0.08
    gesch
    -0.07
    POSITIVE LOGITS
    æ³±
    0.10
    å½ĵæĪij们
    0.10
    认è¯Ĩ
    0.09
     Inhal
    0.09
    inge
    0.09
    æģ¬
    0.09
    åĩıå¼±
    0.09
    æ±ĩ
    0.09
    å¼Ĭ端
    0.09
    dal
    0.08
    Activations Density 0.005%

    No Known Activations