© 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. 52960
    Prev
    Next
    INDEX
    Explanations

    shape and structure

    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
     Blades
    -0.30
    QUI
    -0.27
    itra
    -0.27
    prices
    -0.27
    åłį
    -0.26
     ePub
    -0.25
    .models
    -0.25
    ivities
    -0.25
    iances
    -0.25
    acent
    -0.25
    POSITIVE LOGITS
     form
    0.45
     architecture
    0.39
     l
    0.36
     format
    0.36
     geometry
    0.36
     type
    0.34
     pattern
    0.34
     scheme
    0.34
     method
    0.33
     system
    0.33
    Activations Density 0.051%

    No Known Activations