© 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. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 141214
    Prev
    Next
    INDEX
    Explanations

    technical issues or errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    缺å°ij
    -0.47
    缺失
    -0.42
    missing
    -0.41
     missing
    -0.41
    缺ä¹ı
    -0.40
     Missing
    -0.38
     insufficient
    -0.38
     incomplete
    -0.37
    æ¬łç¼º
    -0.36
    太å°ij
    -0.35
    POSITIVE LOGITS
    æĢ§åij½
    0.30
     sets
    0.30
    ased
    0.28
     Sets
    0.27
    Sets
    0.27
    arma
    0.26
     clusters
    0.25
     ëį
    0.25
     Sher
    0.25
     Asc
    0.25
    Activations Density 56.080%

    No Known Activations