© 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. 53401
    Prev
    Next
    INDEX
    Explanations

    royalty and power

    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
     Leading
    -0.33
    doors
    -0.29
    alse
    -0.25
    Leading
    -0.25
    dcc
    -0.25
     Doing
    -0.24
    fers
    -0.24
    tical
    -0.24
    osas
    -0.24
     Herr
    -0.24
    POSITIVE LOGITS
     following
    0.45
    ä¸ĭåĪĹ
    0.34
    Following
    0.34
    following
    0.32
     Following
    0.32
     Ñģлед
    0.30
     seguint
    0.30
     fol
    0.28
    以ä¸ĭ
    0.28
    ophon
    0.27
    Activations Density 0.042%

    No Known Activations