© 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. 23271
    Prev
    Next
    INDEX
    Explanations

    wreck

    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
    erer
    -0.29
    oir
    -0.28
    ä¼łéĢĴ
    -0.28
    ung
    -0.27
     organ
    -0.27
    .transitions
    -0.26
    ÑĦе
    -0.26
    ERING
    -0.25
    OfWeek
    -0.25
    erate
    -0.25
    POSITIVE LOGITS
     ÑģкаÑĩ
    0.28
    read
    0.27
    åĴĮ个人
    0.27
    olare
    0.26
     read
    0.25
     onSelect
    0.25
    åıijçĶŁäºĨ
    0.24
     Read
    0.24
    icos
    0.24
    panse
    0.24
    Activations Density 0.001%

    No Known Activations