© 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. 162595
    Prev
    Next
    INDEX
    Explanations

    possessive 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
     entirety
    -0.29
    führ
    -0.26
    æĴĻ
    -0.25
    oriously
    -0.25
    antly
    -0.25
     Nhân
    -0.25
    ’↵↵
    -0.24
    æijĨåľ¨
    -0.24
    ком
    -0.24
    大家åĪĨ享
    -0.23
    POSITIVE LOGITS
     progress
    0.32
    è¿Ľåº¦
    0.26
     Past
    0.26
     past
    0.26
    æĪIJå°±
    0.26
    Past
    0.25
     CSS
    0.25
    ä¸įæŃ¢
    0.25
    å®īæİĴ
    0.25
    room
    0.24
    Activations Density 0.002%

    No Known Activations