© 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. 7533
    Prev
    Next
    INDEX
    Explanations

    1

    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
    å¾Ĵ
    -0.30
    ISTA
    -0.28
     undef
    -0.26
    pte
    -0.26
    ystems
    -0.26
    éŃĶ鬼
    -0.25
    _ste
    -0.25
    ä¸įåĪ°
    -0.25
    ë¥ĺ
    -0.24
    даÑĩи
    -0.24
    POSITIVE LOGITS
    elsing
    0.25
    auf
    0.25
    Inline
    0.24
     Playground
    0.24
    åħ³æĢĢ
    0.24
    .Module
    0.24
    aling
    0.24
    rid
    0.23
     risks
    0.23
    enade
    0.23
    Activations Density 0.005%

    No Known Activations