© 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. 12-TRANSCODER-HP
    7. 23812
    Prev
    Next
    INDEX
    Explanations

    Formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _backward
    -0.27
    hort
    -0.27
    weak
    -0.26
    forward
    -0.25
    duct
    -0.25
    éŀł
    -0.25
     throat
    -0.24
    راس
    -0.24
    åij½
    -0.24
     forward
    -0.24
    POSITIVE LOGITS
    Ļ¨
    0.30
     {}:
    0.27
    çİĩ为
    0.26
    ','');↵
    0.25
    :flex
    0.25
     airing
    0.25
    ãİĿ
    0.25
    зе
    0.24
    ’:
    0.24
    %%↵
    0.24
    Activations Density 0.001%

    No Known Activations