© 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. 2677
    Prev
    Next
    INDEX
    Explanations

    magnitude comparison

    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
    åĩĨ
    -0.12
    涣
    -0.11
    ÑģÑħод
    -0.08
    cci
    -0.08
    èĿ¼
    -0.08
     Shack
    -0.08
    ETO
    -0.08
    çľ¼åħī
    -0.08
    åIJ¬äºĨ
    -0.08
    ä¸İåIJ¦
    -0.08
    POSITIVE LOGITS
    æķĪæŀľ
    0.13
     effect
    0.13
    å¹ħ度
    0.12
    æķĪåºĶ
    0.11
     ÑįÑĦÑĦ
    0.10
     Magn
    0.10
     Effect
    0.09
    -effect
    0.09
    ä¸Ģç¬Ķ
    0.09
    ç¨ĭ度
    0.09
    Activations Density 0.332%

    No Known Activations