© 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. 33254
    Prev
    Next
    INDEX
    Explanations

    fully, full, entire, total, complete

    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
    åį§
    -0.09
     Chern
    -0.09
     ÑĤоже
    -0.08
    ä¹Łä¸įéĶĻ
    -0.08
    èijĹ
    -0.08
    emand
    -0.08
    ä¹ĭ乡
    -0.08
    _blank
    -0.08
    thes
    -0.08
    engers
    -0.08
    POSITIVE LOGITS
     fully
    0.16
     full
    0.15
    å®Įæķ´
    0.14
     extent
    0.14
     fullest
    0.14
    full
    0.14
    å®Įæķ´çļĦ
    0.13
    fully
    0.13
    åħħåĪĨ
    0.12
     fullPath
    0.12
    Activations Density 0.069%

    No Known Activations