© 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. 49166
    Prev
    Next
    INDEX
    Explanations

    available

    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
    æ¿ł
    -0.10
    åĽłåľ°
    -0.10
    çĻ¾å¼º
    -0.10
    ä¸į该
    -0.10
    å»ĵ
    -0.09
    æĦı大
    -0.09
    ãģ£ãģĵ
    -0.09
    æĪij没
    -0.09
    æĬķèŀįèµĦ
    -0.09
    è°
    -0.09
    POSITIVE LOGITS
     available
    0.21
    available
    0.16
     availability
    0.15
    _available
    0.15
     Available
    0.15
     disponibles
    0.13
    Available
    0.13
    åı¯ä¾Ľ
    0.12
     AVAILABLE
    0.12
    _AVAILABLE
    0.11
    Activations Density 0.129%

    No Known Activations