© 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. 163178
    Prev
    Next
    INDEX
    Explanations

    telling or explaining

    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
    amburger
    -0.28
     bang
    -0.26
    æī¿
    -0.26
     Pon
    -0.26
     Bounty
    -0.25
    ially
    -0.25
     forming
    -0.24
    éľĨ
    -0.24
     FORM
    -0.24
     ips
    -0.24
    POSITIVE LOGITS
    说æľį
    0.42
    åijĬè¯ī
    0.41
    解éĩĬ
    0.40
    åijĬè¯īä»ĸ
    0.38
     persuade
    0.38
     convince
    0.34
     explaining
    0.33
     explain
    0.33
    åijĬçŁ¥
    0.33
     persuasion
    0.32
    Activations Density 0.007%

    No Known Activations