© 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. 163450
    Prev
    Next
    INDEX
    Explanations

    telling stories

    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
    åħ·ä½ĵåĨħ容
    -0.29
    å¦Ĥä½ķåİ»
    -0.29
    nte
    -0.28
     how
    -0.27
    led
    -0.27
     moderation
    -0.26
    plat
    -0.26
    å¾ħ
    -0.25
     pointers
    -0.24
    ä½ļ
    -0.24
    POSITIVE LOGITS
     pomp
    0.27
    .viewer
    0.25
    æĶ¯çº¿
    0.25
    ÎĪ
    0.25
    çīĽå¥¶
    0.24
    æıIJèµ·
    0.23
    å®ģæĦ¿
    0.23
    bv
    0.23
    第ä¸Ģä½į
    0.23
    ervisor
    0.22
    Activations Density 0.003%

    No Known Activations