© 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. 14-TRANSCODER-HP
    7. 41172
    Prev
    Next
    INDEX
    Explanations

    health, drugs, science

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĴĮåıijå±ķ
    -0.34
    ä¸İåıijå±ķ
    -0.28
    Utc
    -0.27
    á»ĩn
    -0.25
    atable
    -0.25
     LTC
    -0.25
    uality
    -0.24
    ç³ľ
    -0.24
    émon
    -0.24
     commissions
    -0.24
    POSITIVE LOGITS
     initialState
    0.28
    çĬ¶æĢģä¸ĭ
    0.26
     Kn
    0.26
    ouv
    0.26
    Kn
    0.25
     translates
    0.25
    MainFrame
    0.25
     kn
    0.25
    spl
    0.25
    æ´ŀ
    0.25
    Activations Density 0.117%

    No Known Activations