© 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. 7970
    Prev
    Next
    INDEX
    Explanations

    code, programming

    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
    缴æİ¥
    -0.33
    Direct
    -0.32
     Instead
    -0.31
    direct
    -0.30
     Direct
    -0.30
     instead
    -0.30
     direct
    -0.29
    Instead
    -0.29
     diret
    -0.28
     directly
    -0.28
    POSITIVE LOGITS
     pil
    0.29
    elper
    0.28
    lords
    0.27
    对æ¯Ķ
    0.27
     smaller
    0.26
    æį©
    0.26
    ungle
    0.26
     coal
    0.25
    ermen
    0.25
    SystemService
    0.25
    Activations Density 0.086%

    No Known Activations