© 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. 162650
    Prev
    Next
    INDEX
    Explanations

    requests and choices

    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
    ä¹İ
    -0.27
    arrays
    -0.27
    %A
    -0.26
    ints
    -0.26
    obil
    -0.26
    angi
    -0.25
    è¿ľæĻ¯
    -0.25
    idis
    -0.24
    以ä¸ĬçļĦ
    -0.24
    /proto
    -0.24
    POSITIVE LOGITS
    elon
    0.28
    壬
    0.28
     embed
    0.26
     embedded
    0.26
    æľ¯
    0.25
     meth
    0.24
    éľ¹
    0.24
     embedding
    0.23
     only
    0.23
    alia
    0.23
    Activations Density 0.014%

    No Known Activations