© 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. 14-TRANSCODER-HP
    7. 39655
    Prev
    Next
    INDEX
    Explanations

    Names and titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    enment
    -0.27
    atz
    -0.26
    ospace
    -0.26
    apol
    -0.25
    åıijå±ķä¸Ń
    -0.25
    ypo
    -0.25
     merry
    -0.24
    å¸ĤåľºåĮĸ
    -0.24
    ĮĢ
    -0.24
    ока
    -0.24
    POSITIVE LOGITS
    èŃ
    0.29
    å§ijå¨ĺ
    0.25
    çı°
    0.25
    åĮħ袱
    0.24
     cps
    0.24
    ä¸ĭéĿ¢å°±
    0.24
     surfaces
    0.24
    ç³Ł
    0.24
    çłį
    0.24
    缶
    0.24
    Activations Density 0.181%

    No Known Activations