© 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. 7252
    Prev
    Next
    INDEX
    Explanations

    parts ending in 'is'

    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
    sWith
    -0.13
    ish
    -0.13
    s
    -0.11
    6
    -0.10
    9
    -0.10
    4
    -0.10
    iverse
    -0.10
    zilla
    -0.10
    sur
    -0.10
    0
    -0.10
    POSITIVE LOGITS
    cope
    0.12
    ãģ£ãģįãĤĬ
    0.11
    TING
    0.11
    åĽłä¸ºä½ł
    0.10
    rael
    0.10
    å·¾
    0.10
    åĽłä¸ºæĪij
    0.09
    èĵ¼
    0.09
    è¿Ļæł·è¯´
    0.09
    hev
    0.09
    Activations Density 0.112%

    No Known Activations