© 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. 1241
    Prev
    Next
    INDEX
    Explanations

    almost or nearly

    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
    eci
    -0.10
    pps
    -0.09
    åı¦æľī
    -0.09
    忸
    -0.08
     Bark
    -0.08
    sdk
    -0.08
    -License
    -0.08
    磾
    -0.08
     Birch
    -0.08
    iggers
    -0.08
    POSITIVE LOGITS
     impossible
    0.10
    æĺ¯ä¸įåı¯èĥ½
    0.09
    rone
    0.09
    æĹłåı¯
    0.09
    å®Įç¾İçļĦ
    0.09
    OutOfRangeException
    0.09
     PEN
    0.09
    åĵĦ
    0.09
    bai
    0.08
    天é¹ħ
    0.08
    Activations Density 0.011%

    No Known Activations