© 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. 23023
    Prev
    Next
    INDEX
    Explanations

    for

    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
    size
    -0.27
     Returned
    -0.26
    沸
    -0.25
     size
    -0.24
     bod
    -0.24
    oud
    -0.24
     independ
    -0.24
    reetings
    -0.24
    çĤĸ
    -0.23
    å½Ĵ
    -0.23
    POSITIVE LOGITS
    æİĸ
    0.32
    омеÑĢ
    0.27
    als
    0.26
    TEL
    0.25
     hẹ
    0.24
    osal
    0.24
     Saul
    0.24
    综åIJĪæĢ§
    0.24
    æĪ·
    0.24
    ilters
    0.24
    Activations Density 0.004%

    No Known Activations