© 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. 35-TRANSCODER-HP
    7. 40133
    Prev
    Next
    INDEX
    Explanations

    web development/internet content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    navigation
    -0.26
    èĥ½æī¾åĪ°
    -0.25
     vault
    -0.23
    /***/
    -0.23
     discovery
    -0.23
    /Grid
    -0.23
    çĭ¬
    -0.23
    éĥ½éľĢè¦ģ
    -0.23
    模ç³Ĭ
    -0.23
    constexpr
    -0.23
    POSITIVE LOGITS
     Eclipse
    0.25
    缸çĪ±
    0.25
    ä¿®åīª
    0.24
    Chron
    0.24
    plement
    0.24
    åĴ¤
    0.24
    olidays
    0.23
     Pract
    0.23
    ply
    0.23
    eworld
    0.23
    Activations Density 2.076%

    No Known Activations