© 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. 8442
    Prev
    Next
    INDEX
    Explanations

    3

    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
    illator
    -0.25
     MORE
    -0.25
    MORE
    -0.25
    级以ä¸Ĭ
    -0.25
    å¤Ħç½®
    -0.24
     Cres
    -0.24
    .digital
    -0.24
     зани
    -0.24
     EXTRA
    -0.24
    illus
    -0.24
    POSITIVE LOGITS
    iedad
    0.27
    .getLog
    0.27
    _INS
    0.27
    è´¨éĩı
    0.26
    MOTE
    0.26
    TEL
    0.26
    .LookAndFeel
    0.24
    anas
    0.24
    ths
    0.24
    ins
    0.23
    Activations Density 0.076%

    No Known Activations