© 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. 38748
    Prev
    Next
    INDEX
    Explanations

    comparative, raccoons, possums

    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
    uard
    -0.11
    ä»ĸå¦Ī
    -0.10
    ä½ķå¤Ħ
    -0.09
    inke
    -0.09
    OLT
    -0.09
    åij¼
    -0.09
    mans
    -0.09
    EDIA
    -0.09
    lev
    -0.09
    åij½
    -0.09
    POSITIVE LOGITS
    vern
    0.09
    åĭĥåĭĥ
    0.09
    æĸĹ
    0.09
    解éĻ¤
    0.08
    èݽ
    0.08
    latin
    0.08
    å¤ļåľ°
    0.08
    åľ¨äº¬
    0.08
    uration
    0.08
    桶
    0.08
    Activations Density 0.027%

    No Known Activations