© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6827
    Prev
    Next
    INDEX
    Explanations

    entirely followed by intensifier

    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
    ìĬ¤íĬ¸
    -0.09
    çĭĤ
    -0.08
    HEY
    -0.08
    dale
    -0.08
    éĹªåħī
    -0.08
    hey
    -0.08
    éĶ²
    -0.08
    arry
    -0.08
    оÑī
    -0.08
    dx
    -0.07
    POSITIVE LOGITS
    tank
    0.10
    箪
    0.10
    à¸ŀา
    0.10
    otropic
    0.09
    åĩŃçĿĢ
    0.09
    fills
    0.09
    çıł
    0.09
    erm
    0.08
    干货
    0.08
    çłĸ
    0.08
    Activations Density 0.007%

    No Known Activations