© 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. 58345
    Prev
    Next
    INDEX
    Explanations

    Titan-related

    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
    noun
    -0.24
    æijĺ
    -0.24
    bfd
    -0.23
    æµĵåİļ
    -0.23
    æĽ¹æĵį
    -0.23
    eb
    -0.22
    身åŃIJ
    -0.22
    phy
    -0.22
    anner
    -0.22
    ãģľ
    -0.22
    POSITIVE LOGITS
    OU
    0.26
    /fr
    0.26
    ä¸ĵæłı
    0.25
    icap
    0.24
     *(*
    0.24
     Circus
    0.23
    /Open
    0.23
    rink
    0.23
     XII
    0.23
    colm
    0.23
    Activations Density 0.010%

    No Known Activations