© 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. 141423
    Prev
    Next
    INDEX
    Explanations

    giving examples

    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
    éģĵ
    -0.30
    åī¥
    -0.27
    æľ¬èº«çļĦ
    -0.25
    Äĭ
    -0.25
    éĩijèŀįæľºæŀĦ
    -0.24
    NS
    -0.24
    èĩªçIJĨ
    -0.24
    å¤Ħäºİ
    -0.24
    ä¸įå¦Ĥ
    -0.24
     rif
    -0.24
    POSITIVE LOGITS
    ksam
    0.29
     contracting
    0.27
     span
    0.26
     contracted
    0.26
    embro
    0.25
     spans
    0.25
    Span
    0.24
     Pretty
    0.23
    ousse
    0.23
     spanning
    0.23
    Activations Density 12.131%

    No Known Activations