© 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. 96684
    Prev
    Next
    INDEX
    Explanations

    middle

    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
    uhn
    -0.30
    วà¸ģ
    -0.29
    (ln
    -0.28
    vh
    -0.26
    liches
    -0.25
     Welsh
    -0.24
     Fetish
    -0.24
    ä¸įåłª
    -0.24
    çĶ¨æĪ·æıIJä¾Ľ
    -0.24
    ln
    -0.23
    POSITIVE LOGITS
     immediate
    0.31
    adel
    0.28
    Immediate
    0.28
     Immediate
    0.28
     course
    0.27
     courses
    0.27
     coast
    0.27
     Coast
    0.26
     period
    0.25
     immediately
    0.24
    Activations Density 0.103%

    No Known Activations