© 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. 54766
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    çĶĺ
    -0.11
    sei
    -0.10
    åį·
    -0.10
    çŁ¥éģĵèĩªå·±
    -0.10
    porn
    -0.09
    项éĵ¾
    -0.09
    绾
    -0.09
    å·¡
    -0.09
    æºħ
    -0.09
    _RC
    -0.09
    POSITIVE LOGITS
    åĬ¨çĶ»
    0.13
     animated
    0.12
    animated
    0.12
    (animated
    0.11
    Animated
    0.11
     animation
    0.11
     Pixar
    0.11
     Animated
    0.11
    ãĤ¢ãĥĭãĥ¡
    0.10
    举
    0.10
    Activations Density 0.119%

    No Known Activations