© 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. 57249
    Prev
    Next
    INDEX
    Explanations

    runway and speedway

    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
    ened
    -0.10
    å±ĭ顶
    -0.09
    ype
    -0.09
    ãĤ³ãĥ¼ãĥ
    -0.09
    åĽ°æī°
    -0.09
    ifi
    -0.08
    oney
    -0.08
    ail
    -0.08
    idor
    -0.08
    sta
    -0.08
    POSITIVE LOGITS
    ToLocal
    0.09
    éri
    0.09
    èµ°ä¸ĭåİ»
    0.08
    ÑĤÑĢа
    0.08
    rejected
    0.08
    (Thread
    0.08
     Sioux
    0.08
    å®īä¿Ŀ
    0.08
    å¦Ĭ
    0.08
    zin
    0.08
    Activations Density 0.004%

    No Known Activations