© 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. 4456
    Prev
    Next
    INDEX
    Explanations

    upward or downward financial changes

    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
    ssel
    -0.09
    å°Ĭ
    -0.09
    æ¿ĢçĥĪçļĦ
    -0.09
    æ¿ĢçĥĪ
    -0.08
    èĥŀ
    -0.08
    æ³ķéĻ¢
    -0.08
    桧
    -0.08
    稽
    -0.08
    ä¸įéĢļ
    -0.08
    éķ¿æŶéĹ´
    -0.08
    POSITIVE LOGITS
    nets
    0.10
    éªĬ
    0.09
    饮æĸĻ
    0.09
    -net
    0.09
    æµģæĺŁ
    0.09
     (+
    0.08
    pending
    0.08
    avers
    0.08
    _VOID
    0.08
    itt
    0.08
    Activations Density 0.046%

    No Known Activations