© 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. 30273
    Prev
    Next
    INDEX
    Explanations

    bestselling books or authors

    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
    èijµ
    -0.09
    æŀļ
    -0.08
    åĬŁå¤«
    -0.08
    工夫
    -0.08
    å±ķ示
    -0.08
    çĮĹ
    -0.08
    表彰
    -0.08
    NEG
    -0.08
    æĥłåıĬ
    -0.08
    çļĦ强大
    -0.08
    POSITIVE LOGITS
    çķħéĶĢ
    0.16
    æµģè¡Į
    0.12
     bestselling
    0.11
    çĥŃéĶĢ
    0.11
    unner
    0.11
    -hit
    0.10
    åıĹ欢è¿İ
    0.09
    缼è¡Į
    0.09
    åĶ®
    0.09
    imed
    0.09
    Activations Density 0.072%

    No Known Activations