© 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. 162312
    Prev
    Next
    INDEX
    Explanations

    paper

    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
    æĽ´åĥıæĺ¯
    -0.27
     works
    -0.26
     enc
    -0.26
    veillance
    -0.25
     lassen
    -0.25
    catid
    -0.25
    umpt
    -0.25
    ded
    -0.25
    ķĮ
    -0.24
    åĽ¾çīĩæĿ¥æºIJ
    -0.24
    POSITIVE LOGITS
    achel
    0.30
    boy
    0.29
    clip
    0.28
    åıł
    0.27
    stack
    0.26
    wh
    0.25
    -stack
    0.25
    holding
    0.24
    backs
    0.24
    æľŁ
    0.24
    Activations Density 0.008%

    No Known Activations