© 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. 163512
    Prev
    Next
    INDEX
    Explanations

    Beginnings, introductions, timelines

    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
    ä¸Ģ个人
    -0.27
    dess
    -0.26
     ds
    -0.25
    desc
    -0.25
    amo
    -0.25
    аеÑĤÑģÑı
    -0.25
    Once
    -0.25
    ä¸įä¼ļ
    -0.24
    ev
    -0.24
    empre
    -0.24
    POSITIVE LOGITS
    ilan
    0.28
    åį´è¢«
    0.28
    indsight
    0.28
    Textbox
    0.28
    roduced
    0.28
    å°±å¼Ģå§ĭ
    0.28
     became
    0.27
    å·²ä¹ħçļĦ
    0.26
    autiful
    0.26
     stole
    0.26
    Activations Density 0.015%

    No Known Activations