© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5898
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
    éºĴéºŁ
    -0.31
    -members
    -0.27
     der
    -0.27
    æĪIJåijĺåįķä½į
    -0.26
     cad
    -0.26
     receipt
    -0.25
    ,
    -0.25
    鸾
    -0.25
    ites
    -0.25
    uba
    -0.25
    POSITIVE LOGITS
    ÑĢова
    0.26
    ataka
    0.26
    .oracle
    0.25
    stories
    0.25
     STORY
    0.25
    .toFloat
    0.24
    åIJ¹
    0.24
    åĮĢ
    0.24
    angelo
    0.23
    lover
    0.23
    Activations Density 0.022%

    No Known Activations