© 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. 18171
    Prev
    Next
    INDEX
    Explanations

    Far lane / Pharrell Williams

    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
    ery
    -0.10
    eeper
    -0.09
    utable
    -0.09
     latter
    -0.09
    ile
    -0.08
    ãĤį
    -0.08
    aster
    -0.08
    ilter
    -0.08
    3
    -0.08
    itarian
    -0.08
    POSITIVE LOGITS
    thest
    0.13
    stä
    0.10
    mland
    0.10
    æĸ¯åĿ¦
    0.10
    -reaching
    0.10
    好å¤Ħ
    0.10
    åĩłæŃ¥
    0.10
    isy
    0.10
    stead
    0.10
    ighted
    0.09
    Activations Density 0.025%

    No Known Activations