© 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. 95566
    Prev
    Next
    INDEX
    Explanations

    "opt", "pt", "ipt" prefixes

    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
    tics
    -0.28
    ims
    -0.25
    lations
    -0.25
     hier
    -0.25
    ÑģÑĤÑĮ
    -0.24
    agues
    -0.24
    è¾ĥ强çļĦ
    -0.24
    èī¯
    -0.24
    asure
    -0.24
    Sport
    -0.24
    POSITIVE LOGITS
    ery
    0.28
    ermal
    0.26
    RANDOM
    0.26
    engan
    0.25
    ilon
    0.25
    adius
    0.25
    æ··
    0.25
     upp
    0.24
     randomized
    0.24
    enum
    0.24
    Activations Density 0.008%

    No Known Activations