© 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. 162489
    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
     herald
    -0.27
    iets
    -0.26
    VERTISEMENT
    -0.25
     em
    -0.25
     studying
    -0.25
     accompanying
    -0.24
    -pill
    -0.24
    æĴij
    -0.24
     appearing
    -0.23
    anden
    -0.23
    POSITIVE LOGITS
    idia
    0.27
    å°±è¡ĮäºĨ
    0.27
    æĭ¿åĪ°äºĨ
    0.27
    è¿ĻçĤ¹
    0.26
    社
    0.26
    Multip
    0.26
    æĭ¿åĩºæĿ¥
    0.26
    orno
    0.26
    ä¹ĺ
    0.25
    onia
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.