© 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. 162483
    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
    itch
    -0.28
    olic
    -0.27
    çľĭå¾Ĺ
    -0.26
     laws
    -0.26
    ppard
    -0.26
    纵横
    -0.26
    åİ»åĮ»éĻ¢
    -0.25
    eventId
    -0.25
    itter
    -0.25
     rumors
    -0.25
    POSITIVE LOGITS
     collaborators
    0.33
    åħ¶ä»ĸ人
    0.27
    esis
    0.27
    arious
    0.26
    enstein
    0.26
     collabor
    0.26
     collaborative
    0.25
    ãĤıãģijãģ§ãģ¯ãģªãģĦ
    0.25
    :border
    0.25
    çłĶ究人åijĺ
    0.25
    Activations Density 0.002%

    No Known Activations