© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 23614
    Prev
    Next
    INDEX
    Explanations

    Comparison

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    èĥ½è¾¾åĪ°
    -0.34
    aghan
    -0.28
    -placement
    -0.28
    è¾¾
    -0.27
     è¾
    -0.27
    ki
    -0.26
    åIJĪ
    -0.26
    posable
    -0.26
    umu
    -0.25
    达人
    -0.25
    POSITIVE LOGITS
     motivated
    0.31
    vely
    0.28
    earned
    0.27
    eam
    0.26
    wins
    0.25
     Implemented
    0.25
     Muse
    0.24
    _bid
    0.24
     masturb
    0.23
    _CONVERT
    0.23
    Activations Density 0.015%

    No Known Activations