© 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. 23985
    Prev
    Next
    INDEX
    Explanations

    competition, experiments, networks

    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
    åĢĴ
    -0.31
    odal
    -0.27
    oby
    -0.27
    gem
    -0.26
    ç»ĥ
    -0.25
     wards
    -0.25
     adaptations
    -0.24
    advance
    -0.24
    yer
    -0.24
    having
    -0.23
    POSITIVE LOGITS
     about
    0.30
     privately
    0.28
     anonymously
    0.27
    férence
    0.26
     regarding
    0.26
    ifiable
    0.25
    arked
    0.25
     detailed
    0.25
    rit
    0.24
     concerning
    0.24
    Activations Density 0.052%

    No Known Activations