© 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. 54357
    Prev
    Next
    INDEX
    Explanations

    Linnaeus, Lincoln, Linotype

    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
    alysis
    -0.10
    éĻIJãĤĬ
    -0.10
    禾
    -0.10
     todd
    -0.09
    ific
    -0.09
    ibi
    -0.09
     Doll
    -0.09
    DlgItem
    -0.09
    ÙĦاÙĦ
    -0.09
    髯
    -0.09
    POSITIVE LOGITS
    ally
    0.11
    æªİ
    0.10
    arity
    0.10
    coln
    0.10
    ALLY
    0.09
    åıªè¦ģæľī
    0.09
    aming
    0.09
    æĻ°
    0.09
    ä¸Ģ个éĹ®é¢ĺ
    0.09
    upt
    0.08
    Activations Density 0.049%

    No Known Activations