© 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. 23-TRANSCODER-HP
    7. 25105
    Prev
    Next
    INDEX
    Explanations

    CR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diamond
    -0.26
     path
    -0.26
     travelers
    -0.25
     mapping
    -0.25
    .IsNullOrWhiteSpace
    -0.25
     heavy
    -0.25
    éĶ¦
    -0.25
    ley
    -0.24
     melting
    -0.24
     variety
    -0.24
    POSITIVE LOGITS
    amba
    0.35
    .$.
    0.30
    UMB
    0.28
    holder
    0.27
    åIJ»
    0.27
     Honest
    0.26
    chl
    0.25
    çłĶ究åijĺ
    0.25
    åĪ«çļĦ
    0.25
    åºķçĽĺ
    0.25
    Activations Density 0.021%

    No Known Activations