© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3153
    Prev
    Next
    INDEX
    Explanations

    IP address assignment

    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
    Negative Logits
    _flutter
    -0.26
    åĿĿ
    -0.25
    _reaction
    -0.25
    åĭģ
    -0.25
    ropa
    -0.25
    è¿Ľé£Ł
    -0.25
    .React
    -0.24
    partials
    -0.23
    _Matrix
    -0.23
    .ContentType
    -0.23
    POSITIVE LOGITS
     assigned
    0.43
    åĪĨéħį
    0.40
    assigned
    0.38
     reserved
    0.37
     assign
    0.35
     assigns
    0.35
    Assigned
    0.34
     numbers
    0.34
    Assign
    0.33
     Assign
    0.33
    Activations Density 0.076%

    No Known Activations