© 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. 1534
    Prev
    Next
    INDEX
    Explanations

    particular methods and areas

    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
    unde
    -0.27
    æŃ£
    -0.24
    MIT
    -0.24
     lie
    -0.23
    anking
    -0.23
    å¸Ń
    -0.23
    aits
    -0.23
    ä»ħ
    -0.23
    è¶ħ
    -0.23
    å¤į
    -0.23
    POSITIVE LOGITS
    æĽ´è¦ģ
    0.28
    uzu
    0.26
    åĨľåī¯
    0.25
    èĥ½çľĭåĩº
    0.22
     Interpreter
    0.21
     Wig
    0.21
    å¥¥åľ°
    0.21
    è§Ī
    0.21
     PSI
    0.21
    çŀij
    0.21
    Activations Density 0.270%

    No Known Activations