© 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. 56882
    Prev
    Next
    INDEX
    Explanations

    mount points and filesystems

    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
    åįı
    -0.10
    èŁĭ
    -0.09
    è¿Ļ个æĹ¶ä»£
    -0.09
    ç»ķ
    -0.09
    笳
    -0.08
    Jer
    -0.08
    acom
    -0.08
    å®īéĺ³
    -0.08
    ocl
    -0.08
     Eisen
    -0.08
    POSITIVE LOGITS
    filesystem
    0.10
    æĮĤ
    0.10
     Mount
    0.10
    éĿ´
    0.10
     filesystem
    0.09
    éķ£
    0.09
    èĢIJ磨
    0.09
    Unmount
    0.09
     mount
    0.09
    ewing
    0.09
    Activations Density 0.134%

    No Known Activations