© 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. 4821
    Prev
    Next
    INDEX
    Explanations

    single-digit numbers

    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
    IRTUAL
    -0.27
    åĪ«äºº
    -0.26
    icious
    -0.25
    åħ¶å®ĥéĹ®é¢ĺ
    -0.25
     fore
    -0.24
    irtual
    -0.24
    èİ«
    -0.24
    Processing
    -0.24
    èĢĮä¸įæĺ¯
    -0.24
     pork
    -0.24
    POSITIVE LOGITS
    avar
    0.27
    ONO
    0.26
    bell
    0.25
    _intf
    0.25
    inya
    0.25
    opo
    0.25
    è½°
    0.25
     openFileDialog
    0.24
    廨
    0.24
     ATV
    0.24
    Activations Density 0.002%

    No Known Activations