© 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. 163230
    Prev
    Next
    INDEX
    Explanations

    unusual names/places

    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
    sing
    -0.35
    yen
    -0.27
    alement
    -0.27
    enze
    -0.27
    yw
    -0.26
    neck
    -0.26
    istrate
    -0.25
    ioms
    -0.25
     deed
    -0.25
    eel
    -0.25
    POSITIVE LOGITS
    agn
    0.27
    ä¹IJè§Ĥ
    0.25
     picnic
    0.24
     Mali
    0.24
     marsh
    0.23
    resco
    0.23
    翳
    0.23
     joy
    0.23
    agra
    0.23
    ace
    0.23
    Activations Density 0.040%

    No Known Activations