© 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. 40754
    Prev
    Next
    INDEX
    Explanations

    conditions and requirements

    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
    aines
    -0.25
    å·®
    -0.25
    kle
    -0.25
    ousse
    -0.25
    ux
    -0.25
    éĤ£æł·
    -0.24
    emax
    -0.24
    enet
    -0.24
    ston
    -0.24
     executions
    -0.23
    POSITIVE LOGITS
    andi
    0.25
    iron
    0.25
    tl
    0.25
     aficion
    0.24
     persistence
    0.24
    arel
    0.24
    Marshal
    0.24
    uali
    0.24
    opt
    0.23
    olin
    0.23
    Activations Density 0.350%

    No Known Activations