© 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. 107778
    Prev
    Next
    INDEX
    Explanations

    measurement / size

    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
     initialised
    -0.26
    ánh
    -0.25
    çĥŁçģ«
    -0.25
    .writer
    -0.25
    åĦĺ
    -0.24
    İĺìĿ´
    -0.24
    çķĻ
    -0.24
    tered
    -0.24
    Hack
    -0.23
    eria
    -0.23
    POSITIVE LOGITS
     figure
    0.28
     form
    0.28
    enden
    0.27
    dÃŃ
    0.27
    .callback
    0.26
    åħľ
    0.26
     Pare
    0.25
    dia
    0.25
    anden
    0.25
     slip
    0.24
    Activations Density 14.060%

    No Known Activations