© 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. 32136
    Prev
    Next
    INDEX
    Explanations

    Virginia and US states

    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
    éĦŀ
    -0.12
     Kansas
    -0.09
    wright
    -0.09
    ä¹Ŀæ±Ł
    -0.09
    æµĻæ±Ł
    -0.09
    celand
    -0.08
    alic
    -0.08
    mates
    -0.08
    ä¾µåįł
    -0.08
    ssh
    -0.08
    POSITIVE LOGITS
     Virginia
    0.16
    Virginia
    0.16
    京津åĨĢ
    0.16
    æ²³åĮĹçľģ
    0.14
    çŁ³å®¶åºĦ
    0.14
    éĤº
    0.13
    åĨĢ
    0.12
    .azure
    0.12
     Alexandria
    0.12
    éĤ¯éĥ¸
    0.12
    Activations Density 0.236%

    No Known Activations