© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2743
    Prev
    Next
    INDEX
    Explanations

    wanted list, bounty hunters, fugitives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    projectId
    -0.24
    ción
    -0.24
     Trom
    -0.23
    fluence
    -0.22
     Influence
    -0.21
    .onChange
    -0.21
    lig
    -0.21
     teased
    -0.21
    å½¢
    -0.20
    æ°¨
    -0.20
    POSITIVE LOGITS
    æĬĵæįķ
    0.31
    éĢ®æįķ
    0.29
     arrest
    0.28
    Agents
    0.26
    æĹłå£°
    0.24
     arrested
    0.24
    èµ´
    0.23
    ooks
    0.23
     pending
    0.23
     GANG
    0.23
    Activations Density 0.008%

    No Known Activations