© 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. 5054
    Prev
    Next
    INDEX
    Explanations

    Time periods

    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
    assi
    -0.27
    éĢ²
    -0.27
    çĨĦ
    -0.27
    è¿Ľ
    -0.26
    让å®ĥ
    -0.26
    inity
    -0.25
     scor
    -0.25
    è¿Ľåº¦
    -0.24
     frac
    -0.24
    orry
    -0.24
    POSITIVE LOGITS
    uda
    0.30
     thin
    0.30
    å¾®åŀĭ
    0.28
    <ll
    0.28
     Brief
    0.27
    UDA
    0.27
     massive
    0.26
     ëĶ°
    0.26
     Inherits
    0.26
    ä¸ĢæĹı
    0.26
    Activations Density 0.026%

    No Known Activations