© 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. 41193
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    hom
    -0.35
     hom
    -0.31
    er
    -0.27
     week
    -0.27
     homogeneous
    -0.26
    ยาย
    -0.26
    atta
    -0.26
     Week
    -0.25
     Hom
    -0.25
    act
    -0.25
    POSITIVE LOGITS
    ABI
    0.28
    åıij
    0.27
    AZY
    0.25
    kle
    0.25
    åī¯ä¸»ä»»
    0.25
    ils
    0.24
     ÄijáºŃu
    0.24
    -ton
    0.24
     betr
    0.24
    ilenames
    0.24
    Activations Density 0.992%

    No Known Activations