© 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. 57135
    Prev
    Next
    INDEX
    Explanations

    unplug sensible electronics

    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
    çĺħ
    -0.10
    nivers
    -0.09
    _perf
    -0.09
    rottle
    -0.09
    è¾ľè´Ł
    -0.09
    iland
    -0.09
    PLAYER
    -0.09
    /display
    -0.09
    .intent
    -0.09
    常çĶ¨çļĦ
    -0.09
    POSITIVE LOGITS
    æĿ¥ä¸įåıĬ
    0.13
     evacuate
    0.10
    çĸıæķ£
    0.10
     Ping
    0.10
    ä¸įåıĬ
    0.10
     ping
    0.10
    åĩĨå¤ĩ
    0.10
    Ping
    0.09
    ping
    0.09
    åħ¨å®¶
    0.09
    Activations Density 0.061%

    No Known Activations