© 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. 52997
    Prev
    Next
    INDEX
    Explanations

    education

    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
    -n
    -0.27
     poi
    -0.25
     outer
    -0.25
    åŁļ
    -0.25
    евиÑĩ
    -0.24
    ëĭĪ
    -0.24
     NI
    -0.24
     inner
    -0.24
    Ñij
    -0.24
    ¬
    -0.23
    POSITIVE LOGITS
    aks
    0.27
     Chance
    0.26
    赶ä¸Ĭ
    0.26
    	E
    0.26
     Charity
    0.25
    æīģ
    0.25
    è³ĩ
    0.24
    èķ¨
    0.24
     chrom
    0.24
    chrom
    0.23
    Activations Density 0.013%

    No Known Activations