© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53096
    Prev
    Next
    INDEX
    Explanations

    US cities and 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
    éħİ
    -0.10
    SCO
    -0.09
    éħ½
    -0.09
    ä¸Ģæīĭ
    -0.09
    èķ²
    -0.08
    èĩĢ
    -0.08
    strup
    -0.08
    .BASELINE
    -0.08
    éĵī
    -0.08
    è¬ĩ
    -0.08
    POSITIVE LOGITS
    åĬ«
    0.09
    åĽłåľ°
    0.08
    åĨ¤
    0.08
    çĮ©
    0.08
    å½ĵæŶçļĦ
    0.08
    åħij
    0.08
    afia
    0.08
    amma
    0.08
    1
    0.08
    yna
    0.08
    Activations Density 0.247%

    No Known Activations