Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 23-TRANSCODER-HP
    4. 725
    Prev
    Next
    INDEX
    Explanations

    "what is" questions

    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
    äºİæŃ¤
    -0.30
    elm
    -0.30
    æłĵ
    -0.28
    ertain
    -0.26
    è£Ĥ
    -0.26
    åħ¶ä»ĸ
    -0.25
    >this
    -0.25
    encias
    -0.24
    ä¸İæŃ¤
    -0.24
    oria
    -0.24
    POSITIVE LOGITS
    ï¼Ł
    0.33
    ï¼Ł↵↵
    0.30
    æĺ¯ä»Ģä¹Ī
    0.29
    ï¼Ł↵
    0.29
    åıĸãĤĬ
    0.29
    ØŁ
    0.28
    ä½łæĢİä¹Ī
    0.28
     traffic
    0.28
    æĺ¯ä»Ģä¹Īåij¢
    0.26
     ST
    0.26
    Activations Density 0.005%

    No Known Activations