© 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. 163287
    Prev
    Next
    INDEX
    Explanations

    Code/text snippets and conversation

    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
    åīįåı°
    -0.28
    /***/
    -0.27
    avel
    -0.26
    æ¡Ĩæŀ¶
    -0.25
    ÙħØ«ÙĦ
    -0.24
    íķ©
    -0.24
    thon
    -0.24
    ä¸Ģ棵
    -0.24
    -ton
    -0.23
    è°Į
    -0.23
    POSITIVE LOGITS
     soon
    0.28
     afterwards
    0.27
    later
    0.26
     later
    0.26
     busiest
    0.26
     Soon
    0.26
    uddenly
    0.26
    ebb
    0.25
    PointerType
    0.25
    ç´¯äºĨ
    0.25
    Activations Density 0.002%

    No Known Activations