© 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. 40404
    Prev
    Next
    INDEX
    Explanations

    Code and error messages

    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
     widow
    -0.30
     Trait
    -0.27
    inking
    -0.26
    мон
    -0.26
     Stam
    -0.26
    ìļĶ
    -0.25
    apan
    -0.25
    deo
    -0.24
    behavior
    -0.24
    owned
    -0.24
    POSITIVE LOGITS
    ocz
    0.26
     sanct
    0.24
     CHR
    0.24
    èles
    0.24
    orp
    0.24
     snow
    0.23
    æĬ
    0.23
    认è¯ģ
    0.23
    延ç»Ń
    0.23
    ós
    0.23
    Activations Density 2.043%

    No Known Activations