© 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. 27146
    Prev
    Next
    INDEX
    Explanations

    significance, popularity, requirements

    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
    6
    -0.09
    4
    -0.08
    è®°å¾Ĺ
    -0.08
    çī¹åĪ«å£°æĺİ
    -0.08
    7
    -0.08
    ä¸įå°ıå¿ĥ
    -0.08
    缡
    -0.08
    5
    -0.08
    2
    -0.08
    8
    -0.08
    POSITIVE LOGITS
    å¤ļæł·
    0.12
    积æŀģä½ľçĶ¨
    0.11
    è§Ĥ念
    0.11
    åĨħ涵
    0.11
    è¶ĭ
    0.11
    å®ĹæŨ
    0.10
    çIJĨ念
    0.10
    æ·±è¿ľ
    0.10
    åĮ®ä¹ı
    0.10
    æ·±åĮĸ
    0.10
    Activations Density 0.695%

    No Known Activations