© 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. 12-TRANSCODER-HP
    7. 22263
    Prev
    Next
    INDEX
    Explanations

    conjunctions

    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
    åįģä¹Ŀå±Ĭ
    -0.28
    æĸ¯åŁº
    -0.27
    irit
    -0.27
    elle
    -0.27
    èĵĸ
    -0.26
    å²ģ以ä¸ĭ
    -0.25
    esco
    -0.25
    ä¾ĽçĥŃ
    -0.25
    made
    -0.25
    åįģåħ«å±Ĭ
    -0.24
    POSITIVE LOGITS
    atics
    0.29
    isher
    0.25
    scheduled
    0.25
    泪
    0.25
    _ball
    0.24
     theirs
    0.24
     ROUT
    0.24
     routes
    0.24
     administration
    0.24
     compact
    0.23
    Activations Density 0.000%

    No Known Activations