© 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. 163127
    Prev
    Next
    INDEX
    Explanations

    Code and math symbols

    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
    esub
    -0.29
     restTemplate
    -0.27
     kart
    -0.25
    -Encoding
    -0.25
     sniff
    -0.25
    .MenuStrip
    -0.25
    //----------------------------------------------------------------
    -0.24
    EncodingException
    -0.24
    MISS
    -0.24
    ESP
    -0.23
    POSITIVE LOGITS
     scalar
    0.47
    åįķä¸Ģ
    0.45
     Scalars
    0.44
     constant
    0.43
    scalar
    0.42
    Scalar
    0.42
    Scalars
    0.42
    _scalar
    0.40
     scal
    0.40
     constants
    0.40
    Activations Density 0.015%

    No Known Activations