© 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. 48961
    Prev
    Next
    INDEX
    Explanations

    polyester and PET materials

    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
    åķĨä¸ļåĮĸ
    -0.10
    æīĵè¿Ľ
    -0.09
    ãģĹãģŁãĤĤãģ®
    -0.09
    串èģĶ
    -0.09
    ored
    -0.09
    èµį
    -0.08
    ined
    -0.08
    ç»Ħéķ¿
    -0.08
    åı¯æĥ³
    -0.08
    åĶ§
    -0.08
    POSITIVE LOGITS
    æĽ¿
    0.09
    ilha
    0.09
    ç»Ħç»ĩå¼Ģå±ķ
    0.08
    ters
    0.08
    .Features
    0.08
    umba
    0.08
    å¾Īå¤ļäºĭæĥħ
    0.08
    _iterator
    0.08
    信念
    0.08
    çĸ²
    0.08
    Activations Density 0.007%

    No Known Activations