© 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. 41189
    Prev
    Next
    INDEX
    Explanations

    it

    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
    bast
    -0.28
     citas
    -0.28
    eya
    -0.26
    åıįæĺł
    -0.25
    èģĶ
    -0.25
     singles
    -0.25
     jc
    -0.25
    eid
    -0.24
    azine
    -0.24
     conjug
    -0.24
    POSITIVE LOGITS
    ä½ľçī©
    0.29
    .default
    0.28
    亨
    0.27
     default
    0.26
    pose
    0.26
    åħļç»Ħ书记
    0.25
    strand
    0.25
    aries
    0.24
    default
    0.24
     harmless
    0.24
    Activations Density 1.275%

    No Known Activations