© 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. 95650
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    -pe
    -0.32
    pe
    -0.29
     pe
    -0.27
    Ack
    -0.27
     ACK
    -0.26
    åĪĩ
    -0.26
    -separated
    -0.25
    mdir
    -0.25
    asil
    -0.25
     PE
    -0.25
    POSITIVE LOGITS
     dear
    0.27
     financially
    0.27
    fin
    0.27
     Finance
    0.25
     Pruitt
    0.25
    fillType
    0.25
    +=(
    0.25
    FML
    0.24
    outil
    0.24
    ãģĵãĤĮãģĮ
    0.24
    Activations Density 0.005%

    No Known Activations