© 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. 40876
    Prev
    Next
    INDEX
    Explanations

    fundraising events

    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
    lec
    -0.29
    ILog
    -0.27
    igor
    -0.26
    æĦıåIJij
    -0.26
    igo
    -0.26
    çĩŁ
    -0.26
    ingo
    -0.25
    oling
    -0.25
     unic
    -0.24
    ificant
    -0.24
    POSITIVE LOGITS
    pered
    0.33
    download
    0.27
    CHASE
    0.27
    pread
    0.26
     filePath
    0.26
    /temp
    0.25
     downloads
    0.25
     inflamm
    0.25
    è°į
    0.24
    anker
    0.24
    Activations Density 0.072%

    No Known Activations