© 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. 8895
    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
    lined
    -0.29
    rene
    -0.28
    Filed
    -0.28
    çĥŁ
    -0.27
    s
    -0.27
    äºī
    -0.25
    nx
    -0.25
     SIZE
    -0.25
    xes
    -0.25
    rende
    -0.25
    POSITIVE LOGITS
    ég
    0.29
     Nug
    0.26
    åħ¬åı¸å°Ĩ
    0.25
    ergarten
    0.24
     according
    0.24
    hift
    0.24
    _NB
    0.24
    /bower
    0.24
    cade
    0.23
    åľ°æĸ¹æĶ¿åºľ
    0.23
    Activations Density 0.051%

    No Known Activations

    This feature has no known activations.