© 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. 23591
    Prev
    Next
    INDEX
    Explanations

    pathway or signaling systems

    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
    å±¥
    -0.11
    olec
    -0.10
    éħįä¸Ĭ
    -0.09
    çĶŁ
    -0.09
    SEC
    -0.09
    åĦĺ
    -0.08
    CHANGE
    -0.08
    大使
    -0.08
     mass
    -0.08
    acer
    -0.08
    POSITIVE LOGITS
    éĢĶå¾Ħ
    0.14
     pathways
    0.13
    è¿ĻæĿ¡è·¯
    0.12
     pathway
    0.12
    ä¸īæĿ¡
    0.11
    è¿ĻæĿ¡
    0.11
    éĢĶ
    0.11
    è¿Ļå¥Ĺ
    0.11
    产ä¸ļéĵ¾
    0.10
    ä¸ĢæĿ¡
    0.10
    Activations Density 0.611%

    No Known Activations