© 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. 57119
    Prev
    Next
    INDEX
    Explanations

    tulane, tulbagh, tully, azalea, vase

    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
    -0.13
    åijĺ
    -0.10
    utm
    -0.09
    åıijå±ķè§ĦåĪĴ
    -0.09
    asics
    -0.08
    ä¼į
    -0.08
    åħ¶éĹ´
    -0.08
    uter
    -0.08
    /tutorial
    -0.08
    æ°¨éħ¸
    -0.08
    POSITIVE LOGITS
    æĶ»åĬ¿
    0.11
    港åĮº
    0.10
    æĻ°
    0.09
    çķ¹
    0.09
    èģĶèµĽ
    0.09
    å¾Ģäºĭ
    0.09
    boro
    0.09
    åı£å²¸
    0.09
    çŃ
    0.09
    azed
    0.08
    Activations Density 0.006%

    No Known Activations