© 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. 20-TRANSCODER-HP
    7. 140944
    Prev
    Next
    INDEX
    Explanations

    Discussion and commentary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çķĮçļĦ
    -0.33
    éĥģ
    -0.25
    oter
    -0.25
    æīģ
    -0.25
     terre
    -0.25
    é¥ķ
    -0.24
    éĻ¡
    -0.24
     FIRE
    -0.24
    .flat
    -0.24
    MAKE
    -0.24
    POSITIVE LOGITS
    æ¯Ĵ
    0.27
    Sir
    0.27
    ardin
    0.25
    (||
    0.25
    ìĹŃ
    0.25
     décou
    0.23
    èĩªå¦Ĥ
    0.23
    _As
    0.23
    Ĭ¶
    0.23
    -license
    0.23
    Activations Density 27.303%

    No Known Activations