© 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. 40377
    Prev
    Next
    INDEX
    Explanations

    correctness

    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
     Loose
    -0.28
    caps
    -0.27
    _EM
    -0.26
    åĽ½æľī
    -0.25
     flushed
    -0.25
    acio
    -0.24
    arked
    -0.24
    Ñīин
    -0.24
     Commercial
    -0.24
    .compress
    -0.24
    POSITIVE LOGITS
     closure
    0.31
    éºĴéºŁ
    0.28
    closure
    0.28
    cec
    0.26
     power
    0.26
     powers
    0.25
    cef
    0.25
    út
    0.25
    çĪ¬
    0.25
     impact
    0.24
    Activations Density 0.306%

    No Known Activations