© 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. 50202
    Prev
    Next
    INDEX
    Explanations

    suspense thrillers

    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
     Sham
    -0.08
    æ£ł
    -0.08
    èĩªæ²»
    -0.08
    è¾ħ导
    -0.08
    æĢĿè·¯
    -0.08
    rant
    -0.08
    r
    -0.08
    igli
    -0.08
    aised
    -0.08
    产éĶĢ
    -0.08
    POSITIVE LOGITS
    ingly
    0.12
    æĩĤ
    0.11
    ously
    0.09
    éķĽ
    0.09
    _dispatch
    0.09
    海峡
    0.09
    reat
    0.09
    两岸
    0.09
     Äijảo
    0.09
    åIJĬ
    0.09
    Activations Density 0.005%

    No Known Activations