© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19992
    Prev
    Next
    INDEX
    Explanations

    bl followed by vowel

    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
    åİī
    -0.10
     Watkins
    -0.09
    çİĭåŃIJ
    -0.09
    ãĤĭãĤĤãģ®
    -0.09
    orus
    -0.09
    olis
    -0.09
    Wat
    -0.09
    MENT
    -0.09
    åĭ¤
    -0.09
     bows
    -0.09
    POSITIVE LOGITS
    /bl
    0.12
    èŀį
    0.10
    chy
    0.10
     bl
    0.09
     aff
    0.09
    blend
    0.09
    ets
    0.09
    akers
    0.09
    åı¯è°ĵ
    0.08
     апÑĢ
    0.08
    Activations Density 0.016%

    No Known Activations