© 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. 22676
    Prev
    Next
    INDEX
    Explanations

    assign values

    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
     Zuk
    -0.09
    andle
    -0.08
    å¤ķ
    -0.08
    utan
    -0.08
    ieber
    -0.08
    ç¦ıçī¹
    -0.08
    AFE
    -0.08
     aug
    -0.08
    .copyOf
    -0.08
    ÑĦоÑĢ
    -0.08
    POSITIVE LOGITS
    èµĭäºĪ
    0.24
    賦
    0.20
    èµĭ
    0.18
     assigned
    0.16
    (assign
    0.15
    assign
    0.15
    assigned
    0.15
     assign
    0.15
    .assign
    0.14
     assigns
    0.13
    Activations Density 0.108%

    No Known Activations