© 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. 30860
    Prev
    Next
    INDEX
    Explanations

    burial and military personnel

    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
    å¥ĸ
    -0.09
    æķĻä½ł
    -0.09
    .setAuto
    -0.09
    WSC
    -0.08
    ibase
    -0.08
    çī¦
    -0.07
    .getMap
    -0.07
    èĥ½å¾ĹåĪ°
    -0.07
    .mongo
    -0.07
    çĶµæºIJ
    -0.07
    POSITIVE LOGITS
    æŃ»èĢħ
    0.16
    殡
    0.16
    å¢ĵ
    0.15
    èij¬
    0.14
    å°¸
    0.14
    éĢĿ
    0.13
     graveyard
    0.13
     Funeral
    0.12
    å°¸ä½ĵ
    0.12
    åŁĭ
    0.12
    Activations Density 0.069%

    No Known Activations