© 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. 2375
    Prev
    Next
    INDEX
    Explanations

    world leader, -class, -leading, -wide

    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
    eration
    -0.24
    zew
    -0.24
    owanie
    -0.24
    ocene
    -0.23
     PROVIDED
    -0.22
    ismo
    -0.21
    atism
    -0.21
    ÙĬÙĪÙĨ
    -0.21
    æĺ¾å¾Ĺ
    -0.21
     subsection
    -0.21
    POSITIVE LOGITS
     acclaimed
    0.28
    abel
    0.26
    =ax
    0.24
     renowned
    0.24
    -class
    0.24
    -fast
    0.23
    å®ļä¹ī
    0.23
    -tra
    0.23
    称为
    0.22
    -call
    0.22
    Activations Density 0.122%

    No Known Activations