© 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. 24832
    Prev
    Next
    INDEX
    Explanations

    Mixed languages/characters

    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
     realise
    -0.28
     realised
    -0.27
    éľ²åĩº
    -0.26
    Scaled
    -0.25
    amment
    -0.25
    izando
    -0.24
    æĿĥçĽĬ
    -0.24
     centres
    -0.24
    )|
    -0.24
    èµı
    -0.24
    POSITIVE LOGITS
     ins
    0.27
     INS
    0.26
     Operation
    0.26
    _INS
    0.26
    (ins
    0.25
     accident
    0.25
    INS
    0.25
    åıŃ
    0.24
     Reference
    0.24
    Nonnull
    0.24
    Activations Density 0.008%

    No Known Activations