© 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. 7844
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     recip
    -0.28
    rov
    -0.27
    åĤį
    -0.26
    æĢ»ç®Ĺ
    -0.25
    æİī
    -0.25
    追
    -0.25
    æĪij没
    -0.24
    éĽĮ
    -0.24
    assy
    -0.24
    èĩªèIJ¥
    -0.24
    POSITIVE LOGITS
     Lid
    0.30
    fly
    0.27
    flies
    0.25
    hood
    0.25
     lid
    0.24
    ложений
    0.23
    ä¸ŃæľŁ
    0.23
    oleon
    0.23
    .Unlock
    0.23
    uide
    0.23
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.