© 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. 19-TRANSCODER-HP
    7. 7864
    Prev
    Next
    INDEX
    Explanations

    currency symbol

    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
     usually
    -0.28
     straight
    -0.27
     poison
    -0.27
     different
    -0.25
    abo
    -0.25
     normally
    -0.25
     required
    -0.24
    å¼ĥ
    -0.24
    pts
    -0.24
    çł¥
    -0.24
    POSITIVE LOGITS
    çģ«çĥŃ
    0.27
    RY
    0.27
    åħĭèݱ
    0.27
    [top
    0.27
    ;top
    0.25
    å¼¹æĢ§
    0.24
    å¼¹
    0.23
    dam
    0.23
    çıįè´µ
    0.23
    äºĨ
    0.23
    Activations Density 0.048%

    No Known Activations