© 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. 162485
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æ¡£
    -0.27
    åħ¶å®ŀ
    -0.26
    Ep
    -0.26
    åħµ
    -0.25
    °F
    -0.25
     ep
    -0.25
     Rosenberg
    -0.24
    ä¸įåı¯éģ¿åħį
    -0.24
    ously
    -0.24
    lobs
    -0.24
    POSITIVE LOGITS
    ä¾Ŀæĵļ
    0.27
    outline
    0.27
    æĽ²æĬĺ
    0.25
     mixing
    0.25
    breaking
    0.25
    oment
    0.25
    tank
    0.24
    onor
    0.24
    volume
    0.24
    åŃIJéĩĮ
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.