© 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. 162598
    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
    -decoration
    -0.25
     splitted
    -0.25
    èijĹä½ľ
    -0.25
    çĮ¾
    -0.25
    å·¦åı³
    -0.24
    .rpm
    -0.24
    èĦ«
    -0.23
    _easy
    -0.23
    DR
    -0.23
    dao
    -0.23
    POSITIVE LOGITS
    ØŃظ
    0.28
    AIL
    0.27
    аÑħ
    0.26
    ä¿¡æģ¯åıijå¸ĥ
    0.26
    å¯Łçľĭ
    0.25
    BOSE
    0.25
    Property
    0.25
    çļĵ
    0.25
     travers
    0.24
    اة
    0.24
    Activations Density 0.028%

    No Known Activations

    This feature has no known activations.