© 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. 53568
    Prev
    Next
    INDEX
    Explanations

    two units

    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
    æį·
    -0.10
    preced
    -0.09
    é¢į
    -0.09
    AMB
    -0.08
    ä¸ĬäºĨ
    -0.08
     singular
    -0.08
     TY
    -0.08
    Ĭ¶
    -0.08
    loo
    -0.08
    å¾·
    -0.08
    POSITIVE LOGITS
    ä¹ĭéĹ´
    0.16
    ä¹ĭéĹ´çļĦ
    0.15
    ä¸Ģèµ·
    0.14
     together
    0.13
    åľ¨ä¸Ģèµ·
    0.12
    ä¹ĭéĸĵ
    0.12
    äºĴ缸
    0.12
    缸éģĩ
    0.12
    äºĴ
    0.12
     вмеÑģÑĤе
    0.11
    Activations Density 0.345%

    No Known Activations