© 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. 32255
    Prev
    Next
    INDEX
    Explanations

    hidden compartment or pocket

    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
    çļĭ
    -0.14
    è¾ľ
    -0.10
    è°Ĺ
    -0.10
    _TypeInfo
    -0.09
    æĦŁ
    -0.09
    è¡Ĺéģĵ
    -0.09
    abad
    -0.09
    ogo
    -0.09
    èµĪ
    -0.09
    è¾ĸåĮºåĨħ
    -0.09
    POSITIVE LOGITS
    éļIJèĹı
    0.14
     hidden
    0.11
     hiding
    0.11
    éļIJèĶ½
    0.11
    hidden
    0.11
    hide
    0.11
    èĹıçĿĢ
    0.10
    Hidden
    0.10
    ç§ĺå¯Ĩ
    0.10
     cre
    0.09
    Activations Density 0.100%

    No Known Activations