© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6832
    Prev
    Next
    INDEX
    Explanations

    Locations

    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
    tres
    -0.28
     converse
    -0.27
    itals
    -0.26
    ä¸ŃåĽ½çļĦ
    -0.26
    иÑĩно
    -0.25
    ä¸ī代
    -0.25
    venth
    -0.24
     purch
    -0.24
     Pron
    -0.24
    -present
    -0.23
    POSITIVE LOGITS
    åĨ·
    0.30
    æĬĹæĭĴ
    0.28
     sinking
    0.26
    对å¤ĸå¼ĢæĶ¾
    0.25
    TRAIN
    0.25
     doÄŁ
    0.25
    ãĥijãĥ³
    0.25
     amidst
    0.23
    ool
    0.23
    NavigationView
    0.23
    Activations Density 0.022%

    No Known Activations