© 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. 25-TRANSCODER-HP
    7. 108024
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yte
    -0.27
    ite
    -0.27
    en
    -0.27
    roman
    -0.26
    ies
    -0.26
    è¶´åľ¨
    -0.26
    éĥ½èĥ½å¤Ł
    -0.26
    ude
    -0.26
    \Lib
    -0.25
     Bulgarian
    -0.25
    POSITIVE LOGITS
    _menus
    0.28
     molec
    0.27
    Persons
    0.26
    NFL
    0.26
    ä¸Ģ件äºĭ
    0.26
    Locker
    0.25
     therein
    0.25
    QA
    0.24
    轨迹
    0.24
    IBC
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.