© 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. 162662
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ses
    -0.31
    rial
    -0.27
    ukkit
    -0.26
    æĴ¼
    -0.25
    imize
    -0.24
    naments
    -0.24
     obed
    -0.24
    oving
    -0.24
    å°Ħ
    -0.24
     however
    -0.24
    POSITIVE LOGITS
    èĥ´
    0.27
    èĥ¶åĽĬ
    0.26
    enso
    0.25
    ãģ©
    0.25
    çīĪæĿĥæīĢæľī
    0.25
     getResult
    0.24
    åľ£åľ°
    0.24
    æĹ¥çĶµ
    0.23
    Spoiler
    0.23
     curves
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.