© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51727
    Prev
    Next
    INDEX
    Explanations

    cameras and video

    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
    çIJ°
    -0.09
    wares
    -0.09
    æĶ¾åľ¨
    -0.08
    fi
    -0.08
    zap
    -0.08
     Sheridan
    -0.08
    -span
    -0.08
    æIJ´
    -0.08
    æĭį
    -0.08
    æİĮ
    -0.08
    POSITIVE LOGITS
    éĽĦ
    0.12
    åŀĽ
    0.10
    å½ķåĥı
    0.10
    è§Ĩé¢ij
    0.09
    å®īéĺ²
    0.09
    éĺ²çĽĹ
    0.09
    .tf
    0.09
    GOP
    0.09
    cobra
    0.09
    æijĦåĥı头
    0.09
    Activations Density 0.125%

    No Known Activations