© 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. 51764
    Prev
    Next
    INDEX
    Explanations

    nail, nails, nail polish, nail dystrophy, nail-driving

    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
    ally
    -0.12
    ality
    -0.11
    åĬŀåħ¬åİħ
    -0.10
    еÑĢÑĮ
    -0.09
    ed
    -0.09
    海绵
    -0.09
    iny
    -0.09
    毳
    -0.09
    esco
    -0.08
    æģ¿
    -0.08
    POSITIVE LOGITS
    boxes
    0.09
    éĴī
    0.09
    uther
    0.08
    æ©Ľ
    0.08
    ajar
    0.08
    åī
    0.08
    å®Ħ
    0.08
    aton
    0.08
    worm
    0.08
    CORD
    0.08
    Activations Density 0.005%

    No Known Activations