© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12177
    Prev
    Next
    INDEX
    Explanations

    agentstabilizerinsecticidestimulant

    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
    Negative Logits
    /pm
    -0.10
    æ¼Ĩ
    -0.10
    迹
    -0.09
    äºĭåħ³
    -0.08
    _SHA
    -0.08
    é³³
    -0.08
    [of
    -0.08
    bies
    -0.08
    CSI
    -0.08
    å¾Ĺèµ·
    -0.08
    POSITIVE LOGITS
     agent
    0.11
    åīĤ
    0.10
    åħ¼
    0.10
     agents
    0.09
    agent
    0.09
    Agent
    0.09
    æī©åħħ
    0.09
    缸åĬ©
    0.08
    _BOOT
    0.08
    .addElement
    0.08
    Activations Density 0.456%

    No Known Activations