© 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. 58555
    Prev
    Next
    INDEX
    Explanations

    local US news channels

    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
    ÑĢай
    -0.10
    å¼Ľ
    -0.09
    è¿IJæ°Ķ
    -0.09
    ’T
    -0.08
     Klein
    -0.08
     rex
    -0.08
    èµĸ
    -0.08
    èģļä¼ļ
    -0.08
    åĶł
    -0.08
    åİĭè¿«
    -0.08
    POSITIVE LOGITS
    ê¶Į
    0.10
    åĩıéĢŁ
    0.09
    (proc
    0.09
    /rss
    0.09
    çªĹå¸ĺ
    0.08
    äºĨä¸Ģéģį
    0.08
    ä¾Ľ
    0.08
    ocular
    0.08
    ä¾
    0.08
    odox
    0.08
    Activations Density 0.010%

    No Known Activations