© 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. 27-TRANSCODER-HP
    7. 8003
    Prev
    Next
    INDEX
    Explanations

    license/technical documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lest
    -0.26
    使çĶ¨çļĦ
    -0.25
    ä¸Ģçŀ¬éĹ´
    -0.25
     //!<
    -0.24
    _REMOVE
    -0.24
     mil
    -0.24
     hypo
    -0.24
    inqu
    -0.23
    /facebook
    -0.23
    çī¹æ®ĬçļĦ
    -0.23
    POSITIVE LOGITS
    ?key
    0.29
    essler
    0.29
    obel
    0.26
    oller
    0.25
    deg
    0.25
    ripper
    0.24
    tam
    0.24
    è¿Ļä¸įæĺ¯
    0.24
    å¸ĥé²ģ
    0.23
    缼å¼Ģ
    0.23
    Activations Density 0.002%

    No Known Activations