© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 41441
    Prev
    Next
    INDEX
    Explanations

    other

    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
    ours
    -0.30
     breakout
    -0.28
    rat
    -0.28
    adt
    -0.25
     baskets
    -0.24
    reeze
    -0.24
    ört
    -0.24
    æ¿Ģ
    -0.24
    OURS
    -0.24
    rait
    -0.24
    POSITIVE LOGITS
     perpetual
    0.31
     permanently
    0.24
     Posted
    0.24
     LIC
    0.24
    %;"
    0.24
    磾
    0.24
     thr
    0.24
    æĭ©
    0.23
     accompany
    0.23
    _matched
    0.23
    Activations Density 0.044%

    No Known Activations