© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 150649
    Prev
    Next
    INDEX
    Explanations

    is/are

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obe
    -0.27
    —the
    -0.26
     particular
    -0.26
    lle
    -0.26
    olumn
    -0.25
    ä¸ĬäºĨ
    -0.25
    çĻ»éĻĨ
    -0.24
    åĮ»æĬ¤äººåijĺ
    -0.24
    骸
    -0.24
    opers
    -0.23
    POSITIVE LOGITS
    ington
    0.28
    èĩªçĦ¶
    0.28
    æĭĶ
    0.27
    æ§Ĭ
    0.26
    ochrome
    0.25
     pulls
    0.24
    æĭĨ
    0.24
    åħ·
    0.24
    -gap
    0.24
    ForResult
    0.23
    Activations Density 1.326%

    No Known Activations