© 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. 55418
    Prev
    Next
    INDEX
    Explanations

    paint or woodworking processes

    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
    箬
    -0.12
    -hook
    -0.10
    å¹ķ
    -0.09
    èĦį
    -0.09
    åı¹æģ¯
    -0.09
    缯
    -0.09
    unger
    -0.09
    rouch
    -0.09
    sky
    -0.09
     Sho
    -0.09
    POSITIVE LOGITS
    .ordinal
    0.08
    èĵĸ
    0.08
    /respond
    0.08
    ogra
    0.08
    ordinal
    0.08
    åĪ¶åº¦
    0.08
    å¤Ħå¤Ħ
    0.08
    æĭĶ
    0.08
    oen
    0.07
    Lean
    0.07
    Activations Density 0.095%

    No Known Activations