© 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. 57307
    Prev
    Next
    INDEX
    Explanations

    occupant injuries and passengers

    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
    jian
    -0.10
    bic
    -0.09
    æī¿
    -0.09
    åĽ´è§Ĥ
    -0.08
    追赶
    -0.08
    æIJ¬è¿IJ
    -0.08
    èĢľ
    -0.08
     bic
    -0.08
    è·µ
    -0.08
    éĢĢå½¹
    -0.08
    POSITIVE LOGITS
    ä¹ĺ客
    0.15
    座ä½į
    0.13
    座æ¤ħ
    0.12
    座
    0.11
    åĶ®ç¥¨
    0.10
    ä¸ĭ车
    0.10
    åĽ¢åijĺ
    0.10
    车åĨħ
    0.10
    åĿIJ
    0.09
     passengers
    0.09
    Activations Density 0.051%

    No Known Activations