© 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. 4624
    Prev
    Next
    INDEX
    Explanations

    first names followed by last names

    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
    assy
    -0.11
    缴éĢļ车
    -0.09
    æķĿ
    -0.09
    gettext
    -0.08
    äºĭ
    -0.08
    çļĩ宫
    -0.08
     kot
    -0.08
    ##_
    -0.08
    quee
    -0.08
    Ghost
    -0.08
    POSITIVE LOGITS
    åºĬä¸Ĭ
    0.10
    zek
    0.09
    åijľ
    0.09
    (bp
    0.09
    cka
    0.08
    åħ¶ä¸Ńæľī
    0.08
    çĽĺçĤ¹
    0.08
    æĢĻ
    0.08
    çľĩ
    0.08
    _rm
    0.08
    Activations Density 0.166%

    No Known Activations