© 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. 7592
    Prev
    Next
    INDEX
    Explanations

    copyright

    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
    sec
    -0.34
     sk
    -0.31
    as
    -0.29
     sec
    -0.29
    åģ¶
    -0.28
    Ob
    -0.26
    asma
    -0.26
    ton
    -0.26
    rat
    -0.25
    ad
    -0.25
    POSITIVE LOGITS
    æ¿Ĵ
    0.27
     eyed
    0.26
    çĸ±
    0.26
    TYPES
    0.26
     inhabit
    0.25
     insisting
    0.25
    smith
    0.24
    åĬ¨èį¡
    0.24
    earer
    0.24
     inconsist
    0.23
    Activations Density 0.051%

    No Known Activations