© 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. 162502
    Prev
    Next
    INDEX
    Explanations

    Common english verbs

    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
    TZ
    -0.26
    åĻªéŁ³
    -0.26
     trata
    -0.26
    èĢĮçİ°åľ¨
    -0.26
    èīĺ
    -0.24
    åľŁåľ°
    -0.24
    .land
    -0.24
    åħŃ个æľĪ
    -0.24
    agnostic
    -0.24
     sorte
    -0.24
    POSITIVE LOGITS
    å¹¿æ³ĽåºĶçĶ¨
    0.32
     prevalent
    0.31
     prevailing
    0.31
    anyl
    0.30
    hall
    0.29
    常çĶ¨
    0.28
    ssé
    0.28
     prominent
    0.28
     prevail
    0.28
    æĪIJ份
    0.28
    Activations Density 0.002%

    No Known Activations