© 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. 54116
    Prev
    Next
    INDEX
    Explanations

    0

    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
    ’s
    -0.75
    's
    -0.74
    èĢħ
    -0.67
    è¿Ļ
    -0.64
    ’S
    -0.61
    'S
    -0.52
    're
    -0.51
    ’re
    -0.51
    èĢħçļĦ
    -0.48
    èĢħãģ®
    -0.47
    POSITIVE LOGITS
    é¡·
    0.28
    insk
    0.25
    chw
    0.25
    mdat
    0.25
    ematic
    0.24
     interle
    0.23
     Pearce
    0.23
    chai
    0.23
     cons
    0.23
    loe
    0.23
    Activations Density 0.067%

    No Known Activations