© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 36997
    Prev
    Next
    INDEX
    Explanations

    dep

    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
    ously
    -0.11
    uddy
    -0.10
    izer
    -0.09
    -hearted
    -0.09
    ãģĹãģ¾ãģĦ
    -0.09
    æĹ¥æĬ¥ç¤¾
    -0.09
    å¾ī
    -0.08
    ãģıãĤĭ
    -0.08
    ħ
    -0.08
    Ø«
    -0.08
    POSITIVE LOGITS
    ends
    0.12
    ósito
    0.11
    ohl
    0.10
    (dep
    0.09
    loys
    0.09
    çĦ¶æĺ¯
    0.09
    ives
    0.09
    itory
    0.08
     GRE
    0.08
    ole
    0.08
    Activations Density 0.045%

    No Known Activations