© 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. 36092
    Prev
    Next
    INDEX
    Explanations

    directory file list operations

    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
    ç¯ĩç«ł
    -0.10
    没æĥ³åĪ°
    -0.10
    èĦ±
    -0.09
    æĸĻ
    -0.09
    åħ¸éĽħ
    -0.09
    _EOF
    -0.08
    å¢Ļä¸Ĭ
    -0.08
    iasi
    -0.08
    apter
    -0.08
    身åŃIJ
    -0.08
    POSITIVE LOGITS
    .isDirectory
    0.10
    æį¡
    0.09
    æķıæĦŁ
    0.09
    Rename
    0.09
    çĪ¶
    0.09
    _rename
    0.09
    _inode
    0.09
    è¯ŀ
    0.09
     "*.
    0.09
    _mtime
    0.09
    Activations Density 0.628%

    No Known Activations