© 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. 10418
    Prev
    Next
    INDEX
    Explanations

    transmit or receive signals

    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
    noinspection
    -0.10
    æķĻä½ł
    -0.10
    ulk
    -0.09
    IRC
    -0.08
     fragment
    -0.08
    åĪĨæľŁ
    -0.08
     rich
    -0.08
    izr
    -0.08
    å¯Į
    -0.08
    ify
    -0.08
    POSITIVE LOGITS
    hud
    0.10
    éħĬ
    0.09
    çĵĺ
    0.09
    SIDE
    0.09
    çħ§äº®
    0.09
    -side
    0.09
    çĿĢåĬĽ
    0.09
    毽
    0.09
    侧
    0.09
    è·µ
    0.09
    Activations Density 0.070%

    No Known Activations