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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 163783
    Prev
    Next
    INDEX
    Explanations

    Files and data processing

    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
    bang
    -0.27
    eat
    -0.27
    Localized
    -0.27
    gom
    -0.26
    hit
    -0.26
    å°½
    -0.26
     UIB
    -0.26
    ÑħваÑĤ
    -0.25
     hil
    -0.25
     Wyn
    -0.24
    POSITIVE LOGITS
     ”↵↵
    0.30
    äºĨåIJ§
    0.27
    ecz
    0.27
    ãĤĵãģĺãĤĥãģªãģĦãģĭ
    0.24
    /Public
    0.24
    wik
    0.24
    *a
    0.24
    ä¹Łæĺ¯å¦ĤæѤ
    0.24
    ức
    0.23
    .soft
    0.23
    Activations Density 0.011%

    No Known Activations