© 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. 22204
    Prev
    Next
    INDEX
    Explanations

    Technical/Scientific writing

    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
     dank
    -0.28
    _absolute
    -0.26
    +=(
    -0.26
    è¿ĺ羣
    -0.25
    afari
    -0.25
    grund
    -0.25
     Library
    -0.25
    rogen
    -0.25
    âĵĴ
    -0.25
    Ground
    -0.25
    POSITIVE LOGITS
    泡
    0.32
    ip
    0.29
    oure
    0.28
    åIJĬ
    0.27
     next
    0.27
     moment
    0.26
    next
    0.25
    çĭ¬å®¶
    0.25
    à¹Ģà¸Ĺ
    0.25
    iev
    0.25
    Activations Density 0.000%

    No Known Activations