© 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. 35-TRANSCODER-HP
    7. 39624
    Prev
    Next
    INDEX
    Explanations

    distances/lengths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     feet
    -0.42
     hands
    -0.38
     foot
    -0.35
     arms
    -0.35
     yards
    -0.34
     inches
    -0.33
     eyes
    -0.33
     legs
    -0.33
     meter
    -0.33
     inch
    -0.32
    POSITIVE LOGITS
    -mf
    0.34
    -or
    0.34
    Msp
    0.33
    mv
    0.33
    mvc
    0.32
    olon
    0.32
    mn
    0.31
    lj
    0.31
    oa
    0.31
    -dd
    0.31
    Activations Density 10.421%

    No Known Activations