© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8904
    Prev
    Next
    INDEX
    Explanations

    3 or 0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emann
    -0.29
     contrary
    -0.27
    ä¸ĢåĪĩéĥ½æĺ¯
    -0.26
    æĬ«éľ²
    -0.26
    yntax
    -0.25
    nesia
    -0.25
    zzle
    -0.24
    _NAMESPACE
    -0.24
    åIJ¬åIJ¬
    -0.24
     RTE
    -0.23
    POSITIVE LOGITS
    éĩĩ
    0.32
     diced
    0.26
    coming
    0.26
     sampled
    0.26
    çĽijçĿ£æ£ĢæŁ¥
    0.26
     borrowed
    0.25
     royalty
    0.24
    åħ´æĹº
    0.24
    åģļ好
    0.23
     remaining
    0.23
    Activations Density 0.006%

    No Known Activations