© 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. 4813
    Prev
    Next
    INDEX
    Explanations

    scheduling or examination details

    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
    红æĺŁ
    -0.10
    SCI
    -0.09
    è¯Ħæ¯Ķ
    -0.09
    æįī
    -0.09
     Berm
    -0.09
    åį¡å°Ķ
    -0.09
     Sommer
    -0.09
    éĥ¢
    -0.09
     ense
    -0.08
    æĭ¬
    -0.08
    POSITIVE LOGITS
    èĢĥåľº
    0.16
    èĢĥçĶŁ
    0.13
    æĬ¥èĢĥ
    0.11
    å¼Ĥåľ°
    0.11
    ä½ľå¼Ĭ
    0.10
    çĽij
    0.09
    èĢĥçĤ¹
    0.09
    ibt
    0.09
    èĢĥè¯ķ
    0.09
    LAN
    0.08
    Activations Density 0.043%

    No Known Activations