© 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. 33-TRANSCODER-HP
    7. 54125
    Prev
    Next
    INDEX
    Explanations

    letter "b"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cakes
    -0.30
    itas
    -0.29
    åħ·
    -0.29
    labs
    -0.28
     homeowner
    -0.27
    éĺ¶
    -0.27
    ató
    -0.27
     admit
    -0.26
    æĸ½
    -0.26
    èµĬ
    -0.26
    POSITIVE LOGITS
    ancy
    0.28
    ury
    0.25
    dance
    0.25
    apk
    0.25
    orris
    0.25
     Logical
    0.25
     sparing
    0.25
     ник
    0.24
    URY
    0.24
    stem
    0.24
    Activations Density 0.080%

    No Known Activations