© 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. 22727
    Prev
    Next
    INDEX
    Explanations

    research and documentation

    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
     detta
    -0.26
     environ
    -0.25
    cape
    -0.25
    odynamic
    -0.25
    viron
    -0.24
    -det
    -0.24
    ulton
    -0.24
    nak
    -0.24
    ĭè¯ķ
    -0.24
    罩
    -0.23
    POSITIVE LOGITS
    âĢ¢↵↵
    0.32
    *',
    0.29
    .generated
    0.29
    *č↵
    0.28
     –↵↵
    0.28
    .Emit
    0.27
    irs
    0.27
     residue
    0.26
    *",
    0.26
    istrate
    0.26
    Activations Density 0.000%

    No Known Activations