© 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. 32425
    Prev
    Next
    INDEX
    Explanations

    starts with a word followed by a specific token

    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
    ibble
    -0.09
    管家
    -0.09
    adle
    -0.09
    åł°
    -0.09
    ULO
    -0.08
    çĶļèĩ³æĺ¯
    -0.08
    åı¯æĥ³èĢĮçŁ¥
    -0.08
    Paginator
    -0.08
     Christoph
    -0.08
    upo
    -0.08
    POSITIVE LOGITS
    orem
    0.11
    æѤäºĭ
    0.09
    箸
    0.09
    oretical
    0.08
    è¿Ļ个éĹ®é¢ĺ
    0.08
    ä¾¿å®ľ
    0.08
    大åĨĽ
    0.08
    æĩĤäºĭ
    0.08
    bst
    0.08
    ä¸ĢåĪĨéĴŁ
    0.08
    Activations Density 0.270%

    No Known Activations