© 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. 163139
    Prev
    Next
    INDEX
    Explanations

    software development/documentation

    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
    ä¸į失
    -0.31
    atoria
    -0.28
    tracked
    -0.27
     kop
    -0.25
    ponsored
    -0.25
    notated
    -0.24
     wakes
    -0.24
    çĶ¨å¾®ä¿¡
    -0.24
    nÃŃ
    -0.24
    upal
    -0.24
    POSITIVE LOGITS
     but
    0.53
    but
    0.45
    èĢĮæĺ¯
    0.45
    ä½Ĩåį´
    0.44
    ä½Ĩ
    0.43
    åıįèĢĮ
    0.42
    But
    0.41
    ä½Ĩä¹Ł
    0.40
     lắm
    0.40
    ä½ĨçĶ±äºİ
    0.40
    Activations Density 0.012%

    No Known Activations