© 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. 4865
    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
    å¹´æĿ¥
    -0.25
    >tag
    -0.25
    æݧèĤ¡èĤ¡ä¸ľ
    -0.25
     diapers
    -0.25
    [g
    -0.25
     nutshell
    -0.24
    æīįçŁ¥éģĵ
    -0.24
    责任åĪ¶
    -0.24
    imers
    -0.24
    alta
    -0.24
    POSITIVE LOGITS
    (?
    0.29
    vent
    0.28
    ient
    0.27
    iza
    0.26
    ereal
    0.26
     Arch
    0.24
     Circus
    0.24
    /arch
    0.24
    ir
    0.24
     Cir
    0.24
    Activations Density 0.001%

    No Known Activations