© 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. 63063
    Prev
    Next
    INDEX
    Explanations

    suicide attack, prevention, bomber, attempt

    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
    ness
    -0.14
    ç»İ
    -0.10
    çĹ
    -0.09
    nts
    -0.09
    åĦ¿
    -0.09
    arning
    -0.08
    ings
    -0.08
    nil
    -0.08
    tr
    -0.08
    åı£å¾Ħ
    -0.08
    POSITIVE LOGITS
    身亡
    0.12
    ously
    0.11
    念头
    0.10
    /self
    0.10
    éĶı
    0.10
    åīįèĢħ
    0.10
    åĢ¾åIJij
    0.09
    itä
    0.09
    ous
    0.09
    å²Ń
    0.09
    Activations Density 0.012%

    No Known Activations