© 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. 162340
    Prev
    Next
    INDEX
    Explanations

    variety

    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
    æĹ¥åľ¨
    -0.32
    amps
    -0.27
    assa
    -0.27
    iscard
    -0.26
    æµĨ
    -0.26
    çĵ·
    -0.25
    .fil
    -0.25
     prevail
    -0.24
    criptors
    -0.24
    енÑĤа
    -0.24
    POSITIVE LOGITS
    ÅĽ
    0.28
    TestClass
    0.26
    uche
    0.26
    çļĦ帮åĬ©ä¸ĭ
    0.25
    _AT
    0.25
     sometimes
    0.25
     sty
    0.25
    æľī许å¤ļ
    0.24
    ç»ıéªĮ丰å¯Į
    0.24
    fällig
    0.24
    Activations Density 0.066%

    No Known Activations