© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7641
    Prev
    Next
    INDEX
    Explanations

    world

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    亢
    -0.27
     Levine
    -0.27
    çľī
    -0.26
    ulated
    -0.25
    ulate
    -0.25
    ments
    -0.24
    æľĽ
    -0.24
    ðŁı»
    -0.24
    Äĩ
    -0.24
    ps
    -0.23
    POSITIVE LOGITS
    inez
    0.33
    AGER
    0.25
    erus
    0.25
     zaj
    0.25
     apart
    0.25
    views
    0.25
    liness
    0.25
    quake
    0.24
    -slot
    0.24
    -day
    0.23
    Activations Density 1.975%

    No Known Activations