© 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. 33-TRANSCODER-HP
    7. 52953
    Prev
    Next
    INDEX
    Explanations

    scientific research and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scape
    -0.26
    iosk
    -0.26
    sitemap
    -0.25
     crédit
    -0.25
    åĬŀäºĭ
    -0.25
    ounter
    -0.25
    ERAL
    -0.24
     malaysia
    -0.24
     FieldType
    -0.24
    _lib
    -0.24
    POSITIVE LOGITS
    çĪ¸çĪ¸å¦Īå¦Ī
    0.32
     following
    0.31
    -parent
    0.31
     father
    0.31
    Parent
    0.30
     parent
    0.30
    .Parent
    0.29
    çĪ¶è¦ª
    0.29
    å§IJå§IJ
    0.29
     parents
    0.29
    Activations Density 0.014%

    No Known Activations