© 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. 2781
    Prev
    Next
    INDEX
    Explanations

    contact or questions

    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
     mixed
    -0.24
    lexport
    -0.24
     similar
    -0.23
    ä¸Ģå¼ł
    -0.22
     radical
    -0.22
    OrderId
    -0.22
     branches
    -0.21
     cor
    -0.21
     absorbed
    -0.21
    .setSelection
    -0.21
    POSITIVE LOGITS
    åĴ¨è¯¢
    0.37
    çĶµè¯Ŀ
    0.34
     Consult
    0.30
    çŃĶçĸij
    0.29
    éĤ®ç®±
    0.28
     consulting
    0.28
    çĥŃ线
    0.27
     consultant
    0.27
     consult
    0.27
    Consult
    0.26
    Activations Density 0.009%

    No Known Activations