© 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. 8765
    Prev
    Next
    INDEX
    Explanations

    know

    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
    anges
    -0.27
     /↵↵
    -0.26
    å¦Ĥæľīä¾µæĿĥ
    -0.26
    ange
    -0.26
    êt
    -0.25
    ä¹°äºĨ
    -0.25
    gan
    -0.25
    angan
    -0.24
    ↵
    -0.24
    ä¹°
    -0.23
    POSITIVE LOGITS
    VIC
    0.32
    enes
    0.29
    estr
    0.29
     repl
    0.27
     WON
    0.27
    sters
    0.26
     revert
    0.26
    niest
    0.26
    estre
    0.26
    AndHashCode
    0.26
    Activations Density 0.004%

    No Known Activations