© 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. 2187
    Prev
    Next
    INDEX
    Explanations

    Salem, Oregon and Adams

    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
    velle
    -0.23
    è´µ
    -0.21
    ilian
    -0.21
     sophistic
    -0.21
    atic
    -0.21
    íı°
    -0.21
    INLINE
    -0.21
    lux
    -0.21
    亩
    -0.21
    ç²½
    -0.20
    POSITIVE LOGITS
     minded
    0.25
     witches
    0.23
    hue
    0.23
    ä¹ĭæĺŁ
    0.23
    åıįåĵį
    0.22
     Encrypt
    0.21
     Voices
    0.21
    æĺŁæĺŁ
    0.21
     dime
    0.20
    encing
    0.20
    Activations Density 0.007%

    No Known Activations