© 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. 2080
    Prev
    Next
    INDEX
    Explanations

    address numbers or locations

    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
    åĽ½æĥħ
    -0.27
    bum
    -0.26
    __$
    -0.24
    约è°Ī
    -0.24
    India
    -0.22
    .dk
    -0.22
    åIJĮæľŁ
    -0.22
    glass
    -0.22
    åİ¿å§Ķ书记
    -0.22
    Meter
    -0.22
    POSITIVE LOGITS
    åľºåľ°
    0.24
    opies
    0.24
     inverted
    0.24
    &T
    0.24
    æĵİ
    0.23
    éģĵè·¯
    0.23
    åłĨæĶ¾
    0.23
    åłĨ
    0.23
    åĢĴ
    0.23
    马路
    0.23
    Activations Density 0.020%

    No Known Activations