© 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. 6431
    Prev
    Next
    INDEX
    Explanations

    resonance and resonance effects

    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
    ton
    -0.12
    çľ¼çķĮ
    -0.09
    spath
    -0.09
    tons
    -0.09
    mates
    -0.09
    åĴĮåľ°åĮº
    -0.08
    sp
    -0.08
    loader
    -0.08
    ATH
    -0.08
     expos
    -0.08
    POSITIVE LOGITS
    åħ±é¸£
    0.15
    ingly
    0.12
     reson
    0.11
     resonate
    0.10
    åħ±æĮ¯
    0.10
    çĺ¤
    0.10
    ãģ¨ãģĨ
    0.09
    alsy
    0.09
    çł´è£Ĥ
    0.09
    åĵį
    0.09
    Activations Density 0.019%

    No Known Activations