© 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. 18546
    Prev
    Next
    INDEX
    Explanations

    dishes, bottles, jugs, bowls

    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
    ç¾Ĭæ¯Ľ
    -0.10
    èĹ»
    -0.10
     Pant
    -0.09
    äºīåĪĽ
    -0.09
    è¡£
    -0.09
    æĥ³å¿µ
    -0.09
    åĮĹæµ·
    -0.08
    cke
    -0.08
    æĴ
    -0.08
    寡
    -0.08
    POSITIVE LOGITS
    ä¸Ģçĵ¶
    0.13
    壶
    0.12
     bottle
    0.11
    åĸĿéħĴ
    0.11
    éħĴ
    0.11
    çĵ¶
    0.10
     bottles
    0.10
     Bottle
    0.10
     jug
    0.10
    æľ¬ç§ij
    0.10
    Activations Density 0.053%

    No Known Activations