© 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. 37434
    Prev
    Next
    INDEX
    Explanations

    countable noun counts

    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
    eros
    -0.09
     part
    -0.09
    åį¤
    -0.08
    asel
    -0.08
    å·²æľī
    -0.08
    zzo
    -0.08
    ustral
    -0.08
    ãĤ¢ãĤ¦
    -0.08
    å·²ç»ıæľī
    -0.08
    æĪĸå°Ĩ
    -0.08
    POSITIVE LOGITS
    以ä¸ĬçļĦ
    0.13
     davon
    0.11
    åĤį
    0.10
    째
    0.09
    _HEX
    0.09
    ä¸İåħ¶
    0.09
    moth
    0.09
    对åħ¶è¿Ľè¡Į
    0.09
    ToOne
    0.09
    cntl
    0.09
    Activations Density 0.192%

    No Known Activations