© 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. 34824
    Prev
    Next
    INDEX
    Explanations

    scientists who find

    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
    åŁ
    -0.10
    ãģ£ãģįãĤĬ
    -0.10
    vor
    -0.10
    ixo
    -0.09
    éŃĶ鬼
    -0.09
    _RA
    -0.09
    渲
    -0.09
    ë°ĺ
    -0.08
    ancock
    -0.08
    ÅŁa
    -0.08
    POSITIVE LOGITS
    们
    0.13
    /engine
    0.13
    åĢij
    0.13
    们çļĦ
    0.11
    们éĥ½
    0.10
    身å¤Ħ
    0.10
    otle
    0.09
    миÑĢ
    0.09
    åĬ©çIJĨ
    0.09
    éĺŁä¼į
    0.09
    Activations Density 0.010%

    No Known Activations