© 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. 62502
    Prev
    Next
    INDEX
    Explanations

    waiting until for

    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
    StyleSheet
    -0.10
    å¿«æį·
    -0.09
    尽头
    -0.09
    éĤ£åıª
    -0.09
     Sle
    -0.09
    ãĤµãĥ©
    -0.08
    ãĥĬãĥ³
    -0.08
    æĹłçŁ¥
    -0.08
    åĮĻ
    -0.08
    å¾Īå¿«
    -0.08
    POSITIVE LOGITS
    çŃīåĪ°
    0.21
    çŃīå¾ħ
    0.21
     wait
    0.20
    wait
    0.20
     waited
    0.20
     Wait
    0.17
     waits
    0.17
    ä¿Ł
    0.17
     Äijợi
    0.16
    .wait
    0.16
    Activations Density 0.073%

    No Known Activations