© 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. 8087
    Prev
    Next
    INDEX
    Explanations

    characteristic

    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
    ison
    -0.24
     Completely
    -0.23
    æĭ³å¤´
    -0.23
    кладÑĭва
    -0.23
    iences
    -0.23
     Wend
    -0.22
    éģ£
    -0.22
    åıĺéĩı
    -0.21
    使ä¹ĭ
    -0.21
     setDefaultCloseOperation
    -0.21
    POSITIVE LOGITS
    ment
    0.26
    shan
    0.25
    /ex
    0.25
    /use
    0.24
    /dis
    0.24
    shaw
    0.24
    si
    0.24
    sl
    0.24
    sv
    0.23
    led
    0.23
    Activations Density 1.649%

    No Known Activations