© 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. 162509
    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
     оÑĢи
    -0.26
    lock
    -0.25
    forth
    -0.25
    满åĪĨ
    -0.25
    件
    -0.24
     ArgumentOutOfRangeException
    -0.24
    éĶģå®ļ
    -0.24
    Abs
    -0.24
     Locked
    -0.24
     flo
    -0.23
    POSITIVE LOGITS
    lep
    0.32
     findOne
    0.26
    findOne
    0.26
    åĴĦ
    0.25
     única
    0.25
    è´Łæĭħ
    0.25
    Ñīи
    0.25
    ocial
    0.25
    partials
    0.24
    	dest
    0.24
    Activations Density 0.013%

    No Known Activations

    This feature has no known activations.