© 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. 163481
    Prev
    Next
    INDEX
    Explanations

    Reflexive pronouns

    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
    éĻ©
    -0.28
    éĺ´
    -0.28
    cord
    -0.28
    ardless
    -0.27
    ä¸ŃåİŁ
    -0.26
    éĻ°
    -0.26
    éĺ³
    -0.25
    æľ¬
    -0.25
    onal
    -0.24
    ronics
    -0.24
    POSITIVE LOGITS
    SELF
    0.28
    wh
    0.28
    ENTA
    0.27
    ÅĽ
    0.26
    ENT
    0.26
    ãģº
    0.26
    大大å°ı
    0.25
     leading
    0.25
    PING
    0.25
    ighting
    0.24
    Activations Density 0.038%

    No Known Activations