© 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. 35652
    Prev
    Next
    INDEX
    Explanations

    overcoming challenges / problems

    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
    udy
    -0.11
    imen
    -0.10
    UCE
    -0.10
    çĹĽ
    -0.10
    åIJĮå¿ĥ
    -0.10
    utow
    -0.09
     воÑĤ
    -0.09
    verts
    -0.09
    venta
    -0.09
    istribution
    -0.09
    POSITIVE LOGITS
    ä¸įäºĨ
    0.12
    ances
    0.11
    ses
    0.10
    çĸ«æĥħå½±åĵį
    0.10
    able
    0.10
    äºĨæĪijçļĦ
    0.09
    äºĨä»ĸçļĦ
    0.09
    ess
    0.09
    ably
    0.08
    è¢ĸ
    0.08
    Activations Density 0.007%

    No Known Activations