© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161871
    Prev
    Next
    INDEX
    Explanations

    Code namespaces and imports

    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
    orable
    -0.26
    çļĦä¸ĢéĿ¢
    -0.25
    others
    -0.25
     trip
    -0.25
     averages
    -0.24
    以çĤº
    -0.24
    orb
    -0.24
    _AST
    -0.24
     simples
    -0.24
    eft
    -0.23
    POSITIVE LOGITS
    ophile
    0.31
    space
    0.27
     gaz
    0.27
    ud
    0.26
    Space
    0.25
    Deep
    0.25
    _deep
    0.25
     succès
    0.25
    uele
    0.25
    uci
    0.24
    Activations Density 0.026%

    No Known Activations