© 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. 53705
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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
     An
    -0.32
    Ħ件
    -0.29
    ystems
    -0.29
     Th
    -0.26
    uffers
    -0.26
    entai
    -0.25
    -An
    -0.24
    _EXPORT
    -0.24
    称
    -0.24
     variables
    -0.23
    POSITIVE LOGITS
     Didn
    0.49
    Didn
    0.45
     Or
    0.41
     Did
    0.41
    .Or
    0.40
    Or
    0.40
     didn
    0.38
    Did
    0.38
    Was
    0.37
    didn
    0.36
    Activations Density 0.020%

    No Known Activations