© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36047
    Prev
    Next
    INDEX
    Explanations

    bold or boldly

    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
    é¾Ľ
    -0.10
    é»ĺå¥ij
    -0.09
    åľĺ
    -0.09
    åĽ¢
    -0.09
    ç±
    -0.09
    åī§
    -0.09
    èij«èĬ¦
    -0.09
    åĽ¢åijĺ
    -0.09
    è£Ķ
    -0.08
    alem
    -0.08
    POSITIVE LOGITS
     bold
    0.22
    大èĥĨ
    0.21
    èĥĨ
    0.21
    æķ¢äºİ
    0.20
    åĭĩæķ¢
    0.19
    åĭĩäºİ
    0.18
    bold
    0.18
    åĭĩæ°Ķ
    0.18
     Bold
    0.18
    æķ¢
    0.18
    Activations Density 0.035%

    No Known Activations