© 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. 40640
    Prev
    Next
    INDEX
    Explanations

    Code/Licenses

    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
    帳
    -0.27
     quot
    -0.25
    DetailView
    -0.25
    ."+
    -0.25
    éĩijå±±
    -0.25
    пÑĥÑĤ
    -0.25
    .pretty
    -0.24
     Surge
    -0.24
    srv
    -0.24
    硬åĮĸ
    -0.24
    POSITIVE LOGITS
    ocol
    0.30
    åĵĪ
    0.28
    oon
    0.27
    han
    0.27
    ran
    0.27
    æĹ¢
    0.26
    æ±ī
    0.26
     genuinely
    0.26
    haar
    0.26
    Ïħ
    0.25
    Activations Density 0.711%

    No Known Activations