© 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. 37201
    Prev
    Next
    INDEX
    Explanations

    trench raiding, warfare, rooted in

    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
    ÙĦاÙĨ
    -0.09
    liness
    -0.08
    words
    -0.08
    morgan
    -0.08
    åıijå±ķ空éĹ´
    -0.08
    èµ·åĪĿ
    -0.08
    éĻIJãĤĬ
    -0.08
    ous
    -0.08
    hood
    -0.08
    -eslint
    -0.08
    POSITIVE LOGITS
    éĺµåľ°
    0.12
    ä¸Ģä¸ĸ
    0.10
    éĢ¶
    0.10
    座ä½į
    0.09
    apot
    0.09
    åİĨåı²æĸĩåĮĸ
    0.09
     гоÑģ
    0.09
    istr
    0.09
    ä¸ĭæĿ¥çļĦ
    0.08
    以人æ°ij
    0.08
    Activations Density 0.009%

    No Known Activations