© 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. 163180
    Prev
    Next
    INDEX
    Explanations

    size

    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
    chers
    -0.25
    mith
    -0.24
    iac
    -0.24
    ucid
    -0.24
    .logging
    -0.24
    mediately
    -0.24
     жÑĥÑĢнал
    -0.23
    charg
    -0.23
    precation
    -0.23
     ExecutionContext
    -0.23
    POSITIVE LOGITS
    tfoot
    0.30
    è¾ĥ大çļĦ
    0.29
    è¾ĥ大
    0.28
    æ¯Ķè¾ĥ大
    0.28
    太大
    0.27
    é¹ŀ
    0.27
    æĻŁ
    0.26
    ели
    0.26
     tremendous
    0.26
    åĬłå¤§
    0.25
    Activations Density 0.009%

    No Known Activations