© 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. 41212
    Prev
    Next
    INDEX
    Explanations

    Dates and numbers

    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
    .sat
    -0.26
    å®Ī
    -0.26
    chin
    -0.26
     gratuita
    -0.25
     reunion
    -0.25
    åľ¨äº¬
    -0.25
    大åİħ
    -0.24
    éĨ
    -0.24
     ~=
    -0.24
     //~
    -0.24
    POSITIVE LOGITS
    æīĵ好
    0.34
    æµĨ
    0.26
    ÙĨØ©
    0.25
    beat
    0.24
    ação
    0.24
    verts
    0.24
    åijĬ
    0.23
    ÑĤÑı
    0.23
    管çIJĨå·¥ä½ľ
    0.23
    Upgrade
    0.23
    Activations Density 1.732%

    No Known Activations