© 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. 30-TRANSCODER-HP
    7. 96175
    Prev
    Next
    INDEX
    Explanations

    Code and math snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    6
    -0.41
     six
    -0.38
    åħŃ个
    -0.37
     sixth
    -0.35
    åħŃ
    -0.34
    第åħŃ
    -0.33
    six
    -0.32
     Six
    -0.31
    ï¼ĸ
    -0.31
    -six
    -0.31
    POSITIVE LOGITS
    ewith
    0.32
    äºĮåįģ
    0.27
     ante
    0.27
     twenty
    0.26
    iciel
    0.25
    dest
    0.25
    eref
    0.25
    廿
    0.24
    èļģ
    0.24
    tw
    0.24
    Activations Density 0.904%

    No Known Activations