© 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. 30377
    Prev
    Next
    INDEX
    Explanations

    oven and furnace

    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
    ippo
    -0.10
    讨
    -0.09
    佯
    -0.09
    楮
    -0.09
     parach
    -0.08
    ervoir
    -0.08
    èĩªæķij
    -0.08
    åģģ
    -0.08
    inters
    -0.08
    èħ´
    -0.08
    POSITIVE LOGITS
    çĤī
    0.16
    çĥ¤
    0.14
    çĪIJ
    0.14
    çĤĬ
    0.13
    çĥĺ
    0.13
    çģ¶
    0.12
    çĥĺå¹²
    0.12
     oven
    0.12
    çªij
    0.11
     furnace
    0.11
    Activations Density 0.231%

    No Known Activations