© 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. 22317
    Prev
    Next
    INDEX
    Explanations

    Technical questions and code

    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
    Portrait
    -0.25
     nu
    -0.25
     Tracker
    -0.24
     Offline
    -0.23
    mania
    -0.23
     boyc
    -0.23
    Nu
    -0.23
     rad
    -0.23
     ups
    -0.23
    稳å®ļæĢ§
    -0.23
    POSITIVE LOGITS
    yer
    0.31
     controllers
    0.25
    eri
    0.24
    er
    0.24
     arr
    0.24
     ven
    0.24
    ribly
    0.23
    é¼ĵ
    0.23
    еÑĢ
    0.23
    venting
    0.23
    Activations Density 0.000%

    No Known Activations