© 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. 23-TRANSCODER-HP
    7. 24723
    Prev
    Next
    INDEX
    Explanations

    locations, names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edom
    -0.28
    è¿Ļç§į
    -0.25
    éĢīæĭ©
    -0.24
    omain
    -0.23
    éļIJèĶ½
    -0.23
    éĻĩ
    -0.22
     feder
    -0.22
    鼩
    -0.22
    å¢
    -0.22
    ource
    -0.21
    POSITIVE LOGITS
    /generated
    0.28
    CHA
    0.25
    çĨĬ
    0.24
    ots
    0.24
    说æĪij
    0.24
     fair
    0.24
    VK
    0.23
    /mac
    0.23
    åĬłå·¥åİĤ
    0.23
    urdy
    0.23
    Activations Density 0.038%

    No Known Activations