© 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. 32-TRANSCODER-HP
    7. 43252
    Prev
    Next
    INDEX
    Explanations

    technical document text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hel
    -0.27
    éī´å®ļ
    -0.27
    å¾ħ
    -0.27
     Hel
    -0.26
    æĪ·
    -0.25
     Marian
    -0.25
    iu
    -0.24
    ulty
    -0.24
    olynomial
    -0.24
    侧ç»ĵæŀĦæĢ§
    -0.24
    POSITIVE LOGITS
     rav
    0.28
    CCI
    0.27
     chim
    0.26
    CAF
    0.26
    arness
    0.26
    Binder
    0.25
    carbon
    0.24
     fault
    0.24
    -FIRST
    0.24
    adora
    0.24
    Activations Density 0.000%

    No Known Activations