© 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. 31271
    Prev
    Next
    INDEX
    Explanations

    valves and pressure components

    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
    åħħçĶµ
    -0.09
    çĶµéĩı
    -0.09
    çĹ£
    -0.08
    æij¸
    -0.08
    eos
    -0.08
     flatt
    -0.08
    çīµå¼ķ
    -0.08
    é©®
    -0.08
    èįīåľ°
    -0.08
    å¨Ł
    -0.08
    POSITIVE LOGITS
    æݥ管
    0.13
    æ³ķåħ°
    0.13
     plumber
    0.13
    éĺĢ
    0.12
    çļĦåİĭåĬĽ
    0.12
    éĺĢéŨ
    0.11
    åİĭåĬĽ
    0.11
    åłµå¡ŀ
    0.11
    æµģéĩı
    0.10
    主管
    0.10
    Activations Density 0.230%

    No Known Activations