© 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. 19909
    Prev
    Next
    INDEX
    Explanations

    fractal analysis

    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
    以人为
    -0.10
    éĹ·
    -0.09
    CustomAttributes
    -0.09
    å¼ĵ
    -0.09
    okie
    -0.09
     silent
    -0.08
    头顶
    -0.08
    åİ®
    -0.08
    棺
    -0.08
    åĺ§
    -0.08
    POSITIVE LOGITS
     fract
    0.14
    çĶ³
    0.10
    èļķ
    0.09
    å¡Ķ
    0.09
     Koch
    0.09
    /fr
    0.09
    ä¸ī级
    0.08
    urb
    0.08
    combe
    0.08
    饰
    0.08
    Activations Density 0.081%

    No Known Activations