© 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. 22281
    Prev
    Next
    INDEX
    Explanations

    sword-shaped, blue ion, split-seconds complication

    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
    éĶ´
    -0.10
    ResponseStatus
    -0.10
    åĪĨåĪ¥
    -0.10
    åĪĨåĪ«
    -0.09
    caff
    -0.09
    лев
    -0.09
    çī¹æĸ¯
    -0.09
    禧
    -0.09
    ulos
    -0.09
    èij«
    -0.09
    POSITIVE LOGITS
    çł¥
    0.09
     Mär
    0.09
    åĮĹæµ·
    0.09
    梳
    0.09
    ersed
    0.08
    esti
    0.08
     IMM
    0.08
    éĵİ
    0.08
    bern
    0.08
    ULE
    0.08
    Activations Density 0.100%

    No Known Activations