© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20766
    Prev
    Next
    INDEX
    Explanations

    US COURT OF APPEALS

    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
    佬
    -0.11
    liness
    -0.10
    ened
    -0.10
    eenth
    -0.09
    iability
    -0.09
    athan
    -0.08
    ening
    -0.08
    er
    -0.08
    gist
    -0.08
    3
    -0.08
    POSITIVE LOGITS
    ¡
    0.11
    	TokenName
    0.10
    ðŁı»
    0.10
    umbo
    0.10
    arden
    0.09
    ony
    0.09
    ellaneous
    0.09
    åįŁ
    0.09
    ort
    0.09
    irc
    0.09
    Activations Density 0.445%

    No Known Activations