© 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. 11460
    Prev
    Next
    INDEX
    Explanations

    made available or made up

    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
    ingly
    -0.14
    ÙĬات
    -0.11
    edReader
    -0.11
    sWith
    -0.11
    undi
    -0.10
    ued
    -0.09
    à¹Į
    -0.09
    äºĮèĢħ
    -0.09
    hed
    -0.09
    edImage
    -0.09
    POSITIVE LOGITS
    leine
    0.15
    0.12
    imentary
    0.11
    stral
    0.10
    icap
    0.09
    inel
    0.09
    omain
    0.08
    çī¹åĪ«å£°æĺİ
    0.08
    organic
    0.08
    -made
    0.08
    Activations Density 0.050%

    No Known Activations