© 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. 1804
    Prev
    Next
    INDEX
    Explanations

    current context

    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
    åIJĦ家
    -0.09
    åĢ¾æĸľ
    -0.09
    apr
    -0.09
    åIJĦåľ°
    -0.09
    èµĦ产管çIJĨ
    -0.09
    æ½ľèĥ½
    -0.09
    æĸ°é¢ĸ
    -0.09
    atak
    -0.09
    ily
    -0.09
    èľļ
    -0.09
    POSITIVE LOGITS
    å½ĵåīį
    0.16
     current
    0.15
     ÑĤекÑĥÑī
    0.14
    current
    0.13
    .current
    0.12
    	current
    0.10
     íĺĦìŀ¬
    0.10
    _current
    0.10
    æŃ£åľ¨
    0.10
    CURRENT
    0.10
    Activations Density 0.467%

    No Known Activations