© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52699
    Prev
    Next
    INDEX
    Explanations

    hide, camouflage, disguise

    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
    ufs
    -0.10
    ogie
    -0.10
    ä¸įè¿ľ
    -0.10
    åİ©
    -0.10
    åıĭæĥħ
    -0.10
    端æŃ£
    -0.09
    éķ¿å¤§
    -0.09
    çļĦçĪ±æĥħ
    -0.09
    è½±
    -0.09
    æĦŁåħ´è¶£çļĦ
    -0.09
    POSITIVE LOGITS
    éļIJ身
    0.18
    伪è£ħ
    0.14
    _hide
    0.13
     camouflage
    0.13
    éļIJå½¢
    0.13
    éļIJèĹı
    0.13
     hide
    0.13
    éļIJèĶ½
    0.13
    .hide
    0.12
     hiding
    0.12
    Activations Density 0.067%

    No Known Activations