© 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. 163213
    Prev
    Next
    INDEX
    Explanations

    Academic/Technical texts

    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
    /GL
    -0.27
    çĪ¶åŃIJ
    -0.26
    wan
    -0.25
    主管éĥ¨éŨ
    -0.24
    /var
    -0.24
    è¿ĺæĥ³
    -0.24
            ↵        ↵        ↵
    -0.23
    /*----------------------------------------------------------------------------
    -0.23
    æł
    -0.23
    æķ£
    -0.23
    POSITIVE LOGITS
    eten
    0.28
    those
    0.25
     lawyers
    0.25
    æįŁ
    0.24
     frequently
    0.24
    åħŃ个æľĪ
    0.24
    åįģ大
    0.24
     namedtuple
    0.23
    uffix
    0.23
    äºĶå¹´
    0.23
    Activations Density 0.001%

    No Known Activations