© 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. 19773
    Prev
    Next
    INDEX
    Explanations

    four horsemen or fourth circuit

    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
    alach
    -0.10
    æ»ĵ
    -0.09
    ãģ®ãģ¯
    -0.09
    ãģªãģĬ
    -0.09
    IRO
    -0.09
    ãģ®ãģĮ
    -0.08
    opaque
    -0.08
    æĺ¯
    -0.08
    åħ¶æ¬¡
    -0.08
    earch
    -0.08
    POSITIVE LOGITS
    teenth
    0.23
    teen
    0.23
    ly
    0.17
    ness
    0.16
    mente
    0.15
    ality
    0.14
    ../../../
    0.14
    ific
    0.14
    iers
    0.14
    nt
    0.13
    Activations Density 0.030%

    No Known Activations