© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 3455
    Prev
    Next
    INDEX
    Explanations

    executioner or guillotine

    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
    CEED
    -0.10
    èľĤèľľ
    -0.09
    uren
    -0.09
    belt
    -0.09
     sơ
    -0.09
    æī©å»º
    -0.09
    acin
    -0.08
     Redistributions
    -0.08
     há»Ļi
    -0.08
     rekl
    -0.08
    POSITIVE LOGITS
    çłį
    0.12
     head
    0.12
     Head
    0.11
    éĵ¡
    0.11
     severed
    0.11
    Head
    0.10
    å¹²åĩĢ
    0.10
    æĸ«
    0.10
     Heads
    0.10
    head
    0.10
    Activations Density 0.063%

    No Known Activations