© 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. 95757
    Prev
    Next
    INDEX
    Explanations

    say "than"

    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
    èĥ½åIJ¦
    -0.26
    ystal
    -0.26
    -quarter
    -0.26
    缺å°ij
    -0.26
    ioms
    -0.25
    &&!
    -0.25
    ectl
    -0.24
     ourselves
    -0.24
     oczywiÅĽcie
    -0.24
    chemy
    -0.24
    POSITIVE LOGITS
     autogenerated
    0.30
     generated
    0.28
    æīĢ产çĶŁçļĦ
    0.28
    toMatchSnapshot
    0.28
     compared
    0.27
    baum
    0.26
    åı¯èĥ½åıijçĶŁ
    0.26
     Bookmark
    0.25
     exposures
    0.25
     strokeWidth
    0.25
    Activations Density 0.911%

    No Known Activations