© 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. 6729
    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
    åīįåĩłå¹´
    -0.33
    bery
    -0.31
     boob
    -0.27
    ä¸Ńæłĩ
    -0.27
    ::.
    -0.27
    .mixin
    -0.26
    .sourceforge
    -0.26
    ataire
    -0.25
    综åIJĪæ²»çIJĨ
    -0.24
    缴å¾Ħ
    -0.24
    POSITIVE LOGITS
    纪
    0.30
    ŀæĢ§
    0.27
    patial
    0.27
    collapsed
    0.26
    walker
    0.25
    ç¯ĩ
    0.25
    аÑĨион
    0.24
    itting
    0.24
     COLL
    0.24
    ä¹ī
    0.24
    Activations Density 0.009%

    No Known Activations

    This feature has no known activations.