© 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. 1740
    Prev
    Next
    INDEX
    Explanations

    Schottky barrier, energy barrier

    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
    ensation
    -0.09
    tober
    -0.09
    æ´ª
    -0.09
    踵
    -0.09
    å®ļä½į
    -0.09
    Boom
    -0.08
    åĨįéĢł
    -0.08
    ä¸Ģè·¯
    -0.08
    _rl
    -0.08
    ç°ĩ
    -0.08
    POSITIVE LOGITS
    éĹ¨æ§Ľ
    0.23
    åĩĨåħ¥
    0.17
    å£ģåŀĴ
    0.16
     barriers
    0.16
     barrier
    0.15
    éļľç¢į
    0.13
     Barrier
    0.12
    å±ıéļľ
    0.11
    _barrier
    0.11
    éļľ
    0.11
    Activations Density 0.190%

    No Known Activations