© 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. 27-TRANSCODER-HP
    7. 8663
    Prev
    Next
    INDEX
    Explanations

    Code/copyright related texts

    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
    GridView
    -0.27
     Traditional
    -0.24
    éľ°
    -0.24
    ueil
    -0.24
     profiles
    -0.23
    ouble
    -0.23
     ideal
    -0.23
    columnName
    -0.23
    ataires
    -0.23
    arging
    -0.23
    POSITIVE LOGITS
    éĿ©åij½
    0.27
    éļĺ
    0.26
    ixon
    0.25
     uninitialized
    0.25
     zeroes
    0.25
    åĴĢ
    0.25
    绵
    0.24
     twist
    0.24
    æĿ¾
    0.24
     lick
    0.23
    Activations Density 0.005%

    No Known Activations