© 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. 57574
    Prev
    Next
    INDEX
    Explanations

    recognition of various specific entities

    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
    çĦ¶æĺ¯
    -0.11
    ãģĤãĤĭ
    -0.10
    æł·çļĦ
    -0.10
    able
    -0.10
    edly
    -0.10
    ãģĮãĤī
    -0.10
    lient
    -0.10
    abal
    -0.09
     cứ
    -0.09
    ãĢħ
    -0.09
    POSITIVE LOGITS
    ×ķת
    0.12
    halb
    0.12
    ened
    0.12
    ities
    0.11
    istic
    0.11
    eus
    0.10
    enton
    0.10
     ë¶Ī구íķĺê³ł
    0.10
    è§İ
    0.10
    æªĶ
    0.10
    Activations Density 0.270%

    No Known Activations