© 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. 38187
    Prev
    Next
    INDEX
    Explanations

    occupancy and occupational terms

    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
    fully
    -0.12
    ovel
    -0.11
    born
    -0.10
    -0.10
    iac
    -0.10
    tle
    -0.09
    icult
    -0.09
    _oc
    -0.09
    è··
    -0.09
    isen
    -0.09
    POSITIVE LOGITS
    èĩªå¦Ĥ
    0.11
    çĦ¶æĺ¯
    0.11
    ied
    0.10
    ../
    0.09
    à¸Ńาศ
    0.09
    ôt
    0.09
    Ţ
    0.09
    纩
    0.09
    累累
    0.09
    berman
    0.09
    Activations Density 0.030%

    No Known Activations