© 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. 23166
    Prev
    Next
    INDEX
    Explanations

    snow

    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
    .aspect
    -0.28
    ấn
    -0.28
    è¼Ŀ
    -0.26
    èħ¾é£ŀ
    -0.25
    razil
    -0.25
     arou
    -0.24
     bá»ķ
    -0.24
     databases
    -0.24
     motivational
    -0.24
     táºŃn
    -0.24
    POSITIVE LOGITS
     median
    0.27
     Median
    0.27
    Median
    0.27
     HttpHeaders
    0.27
    éĺĦ
    0.26
     Survey
    0.24
    éĹ®ä»ĸ
    0.24
    询éĹ®
    0.24
    追éĹ®
    0.24
    åѦåŃIJ
    0.23
    Activations Density 0.000%

    No Known Activations