© 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. 9571
    Prev
    Next
    INDEX
    Explanations

    "tend to"

    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
    åı¯ä¸įæĺ¯
    -0.09
    æĽ¾
    -0.09
    åĩłä¹İ
    -0.08
    æĽ¾åľ¨
    -0.08
    æij
    -0.08
    ÑĢез
    -0.08
    诸å¦Ĥ
    -0.08
    wat
    -0.08
    ilm
    -0.07
    ä¿Ĺ称
    -0.07
    POSITIVE LOGITS
    onth
    0.10
    èµį
    0.10
    ITIONAL
    0.10
    ureka
    0.10
    noinspection
    0.10
    ower
    0.10
    /is
    0.09
    éķ¿çĽ¸
    0.09
    afil
    0.09
    ahir
    0.09
    Activations Density 0.005%

    No Known Activations