© 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. 14-TRANSCODER-HP
    7. 41330
    Prev
    Next
    INDEX
    Explanations

    blog posts with dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çªģåıij
    -0.29
    çľģæĶ¿åºľ
    -0.27
    MER
    -0.26
    å±Ģéķ¿
    -0.25
    éĶĻè¿ĩ
    -0.25
     quota
    -0.25
     pads
    -0.25
    _AHB
    -0.24
    éĶĻè¿ĩäºĨ
    -0.24
     Ñģебе
    -0.24
    POSITIVE LOGITS
    ìĺ·
    0.27
    utton
    0.26
    phis
    0.25
    ope
    0.25
     Disclosure
    0.24
    itch
    0.24
    .OP
    0.24
    èijĨ
    0.24
    人äºĭ
    0.24
    ust
    0.23
    Activations Density 2.097%

    No Known Activations