© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6153
    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
    å¹²èĦĨ
    -0.31
    端æŃ£
    -0.27
    å¤ļ个
    -0.25
    æµĵ缩
    -0.25
    -collapse
    -0.25
     arbit
    -0.24
     shorthand
    -0.23
     chức
    -0.23
    ä¸ªå·¥ä½ľæĹ¥
    -0.23
     protections
    -0.22
    POSITIVE LOGITS
     Charging
    0.27
    hor
    0.25
    豪
    0.24
     HOR
    0.24
    borg
    0.24
     Prop
    0.24
    eel
    0.24
    çļĦæ¯į亲
    0.24
    轸
    0.23
    cé
    0.23
    Activations Density 3.687%

    No Known Activations

    This feature has no known activations.