© 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. 40644
    Prev
    Next
    INDEX
    Explanations

    Legal/academic documents

    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
    sek
    -0.28
     higher
    -0.27
    èģĮåĬ¡
    -0.26
    HttpContext
    -0.26
     beg
    -0.25
    姿
    -0.25
     merit
    -0.25
    å´
    -0.24
    celand
    -0.24
     behind
    -0.24
    POSITIVE LOGITS
    Ignoring
    0.28
    èŁĭ
    0.28
     rex
    0.25
    éĿĴå±±
    0.25
    Logo
    0.24
    åħįè´£
    0.24
    moth
    0.24
     buurt
    0.24
     Lon
    0.23
    çīº
    0.23
    Activations Density 0.306%

    No Known Activations