© 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. 22444
    Prev
    Next
    INDEX
    Explanations

    varied and unstructured text

    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
     lief
    -0.26
    sted
    -0.25
    ismatic
    -0.25
    è¿ĻçĤ¹
    -0.24
    species
    -0.24
    fly
    -0.24
    æĤł
    -0.24
    cy
    -0.23
    ä¹ĭä¸Ģ
    -0.23
    åĵģçīĮ形象
    -0.23
    POSITIVE LOGITS
    _placeholder
    0.27
     Packs
    0.26
    _BT
    0.25
    RAIN
    0.25
    èĦī
    0.24
     Bund
    0.24
     pulse
    0.24
    ë²Ķ
    0.24
    inqu
    0.24
    å¢Ļ
    0.24
    Activations Density 0.000%

    No Known Activations