© 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. 4120
    Prev
    Next
    INDEX
    Explanations

    long, short, or intermediate term

    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
     Brend
    -0.09
    ä¼ĺäºİ
    -0.08
    é²Ľ
    -0.08
    æĶĢçĻ»
    -0.08
    ested
    -0.08
     epis
    -0.08
    两次
    -0.08
    çĻ»
    -0.08
    ç¥ī
    -0.08
    èĭij
    -0.08
    POSITIVE LOGITS
    çŁŃæľŁ
    0.12
    éķ¿è¿ľ
    0.12
    çŁŃæľŁåĨħ
    0.12
    .medium
    0.11
    igan
    0.10
    าว
    0.10
    ilater
    0.09
    medium
    0.09
     medium
    0.09
    SHORT
    0.09
    Activations Density 0.036%

    No Known Activations