© 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. 18548
    Prev
    Next
    INDEX
    Explanations

    R-CNC150, Z10, Outlander

    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
    èķĥ
    -0.08
    åľ°æłĩ
    -0.08
    ç»ĦåĽ¾
    -0.08
    aci
    -0.08
    æĪ¿ä¸ľ
    -0.08
    æĤį
    -0.08
    äºĨä¸Ģéģį
    -0.08
    NonNull
    -0.08
    ause
    -0.08
    hos
    -0.08
    POSITIVE LOGITS
    åıĬåħ¶
    0.10
    posable
    0.10
    ä¸İåħ¶
    0.09
    åĪĿ
    0.09
    urrection
    0.09
    æľ´å®ŀ
    0.09
    æĹ¢æĺ¯
    0.08
    æ¯Ķèµ·
    0.08
    身ä¸Ĭ
    0.08
    æŀģéĻIJ
    0.08
    Activations Density 0.076%

    No Known Activations