© 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. 41110
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    æµģåĬ¨æĢ§
    -0.31
    æ¤ħ
    -0.27
    åı¥
    -0.27
    çĵ¶
    -0.26
    确认
    -0.26
    >Welcome
    -0.26
     collaborators
    -0.25
    姣
    -0.25
    çĪ±å¥½
    -0.25
    æİĮ声
    -0.25
    POSITIVE LOGITS
    azu
    0.29
     sliced
    0.26
    ellant
    0.25
     Hale
    0.24
     axial
    0.24
    Digest
    0.24
    Reach
    0.24
    mentioned
    0.24
    .seek
    0.23
    acea
    0.23
    Activations Density 0.130%

    No Known Activations