© 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. 162503
    Prev
    Next
    INDEX
    Explanations

    title

    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
    ael
    -0.28
    sher
    -0.27
    eor
    -0.27
    dia
    -0.27
    regor
    -0.26
    ä¸Ī
    -0.26
    ä¸įåħĭä¸įåıĬ
    -0.25
    airo
    -0.25
    aeda
    -0.24
    corr
    -0.24
    POSITIVE LOGITS
    ersion
    0.29
    bring
    0.28
    /wiki
    0.27
    aminer
    0.26
    /rs
    0.25
    ism
    0.25
     Maiden
    0.24
     post
    0.24
    .one
    0.24
     maps
    0.24
    Activations Density 0.005%

    No Known Activations