© 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. 163130
    Prev
    Next
    INDEX
    Explanations

    was

    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
    anches
    -0.28
    utes
    -0.28
    çħ§äº®
    -0.28
    ights
    -0.27
    ght
    -0.25
    Focus
    -0.25
    hton
    -0.25
    focus
    -0.25
    á»ĩp
    -0.24
    -motion
    -0.24
    POSITIVE LOGITS
     $('#'
    0.27
    (padding
    0.25
    _STAGE
    0.24
    è¿«ä¸įåıĬå¾ħ
    0.24
     $("#"
    0.24
    _paths
    0.23
     stage
    0.23
    é²Ł
    0.23
    æİ£
    0.23
    LError
    0.23
    Activations Density 0.010%

    No Known Activations