© 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. 32287
    Prev
    Next
    INDEX
    Explanations

    crowd

    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
    åħį
    -0.09
     Rew
    -0.08
    åħ»æĪIJ
    -0.08
    æĹłæĥħ
    -0.08
    abled
    -0.08
     Grove
    -0.08
    带åĬ¨
    -0.08
    UCH
    -0.08
    ç®ĢåİĨ
    -0.08
    åīij
    -0.08
    POSITIVE LOGITS
     crow
    0.14
    æĭ¥æĮ¤
    0.13
    crow
    0.12
    çĻ»
    0.10
    åľ°ä¸Ń
    0.10
    èģļéĽĨ
    0.10
     Crow
    0.10
    åĽ´è§Ĥ
    0.10
    Crow
    0.10
    cha
    0.09
    Activations Density 0.046%

    No Known Activations