© 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. 2711
    Prev
    Next
    INDEX
    Explanations

    javadoctor javascript documentation

    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
    æµģæ°´
    -0.28
    ENE
    -0.25
    æĪ·
    -0.25
    æĪ·åı£
    -0.24
    æĹłäºº
    -0.23
    éĢģè´§
    -0.22
     Outlet
    -0.22
    åĩłæŃ¥
    -0.22
    iped
    -0.22
    NECTION
    -0.21
    POSITIVE LOGITS
    饰
    0.26
     modifiers
    0.24
    åĺĺ
    0.24
     equivalents
    0.24
    ä¹Łå¥½
    0.23
    å®ĿçŁ³
    0.23
     standards
    0.23
    -plugin
    0.22
    è§ĦåĪĻ
    0.22
    ä¼ĺåħĪ
    0.22
    Activations Density 0.118%

    No Known Activations