© 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. 9043
    Prev
    Next
    INDEX
    Explanations

    Types of people

    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
    è¡°
    -0.30
    stellen
    -0.26
    ç²¾è£ħ
    -0.26
    åĿı
    -0.25
    åħ³åı£
    -0.25
    æľªæĪIJ
    -0.24
    åĽłåľ°
    -0.24
     ll
    -0.24
     staffers
    -0.24
     Officials
    -0.24
    POSITIVE LOGITS
    ì£Ħ
    0.27
    INCLUDED
    0.25
    寤
    0.24
     exclusive
    0.23
    פת
    0.23
    æ®Ĭ
    0.23
    iram
    0.23
    ippet
    0.23
    æģ»
    0.23
    ALSE
    0.23
    Activations Density 0.102%

    No Known Activations