© 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. 163150
    Prev
    Next
    INDEX
    Explanations

    business market reports

    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
     counterpart
    -0.27
    currentColor
    -0.27
    iren
    -0.26
    crop
    -0.26
     masse
    -0.25
    ÑĮ
    -0.25
    yg
    -0.25
    Mass
    -0.25
    extras
    -0.25
    éĻIJæŶ
    -0.24
    POSITIVE LOGITS
    psy
    0.28
    åŃĺ
    0.25
    compound
    0.25
    okay
    0.25
    çľĭåĪ°äºĨ
    0.25
    .pb
    0.24
    ITUDE
    0.24
     pie
    0.23
    ök
    0.23
     Compound
    0.23
    Activations Density 0.009%

    No Known Activations