© 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. 57186
    Prev
    Next
    INDEX
    Explanations

    lock and key

    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
    DG
    -0.09
    asan
    -0.09
    akis
    -0.09
    adder
    -0.09
     Aren
    -0.09
     Boiler
    -0.09
    象
    -0.09
    abr
    -0.08
    ä¸įç¡®å®ļ
    -0.08
    dad
    -0.08
    POSITIVE LOGITS
    éĶģ
    0.16
    解éĶģ
    0.16
     unlock
    0.15
    éĴ¥åĮĻ
    0.14
     unlocked
    0.14
     lock
    0.14
    _UNLOCK
    0.14
     locks
    0.14
     unlocking
    0.14
     Lock
    0.13
    Activations Density 0.072%

    No Known Activations