© 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. 149752
    Prev
    Next
    INDEX
    Explanations

    coding documentation

    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
     indirect
    -0.28
     prior
    -0.27
     Switzerland
    -0.26
    åĬŀ
    -0.25
    ifix
    -0.25
    éĹ´æİ¥
    -0.24
     Hor
    -0.24
    éĵº
    -0.24
    atis
    -0.23
     Tanzania
    -0.23
    POSITIVE LOGITS
    cion
    0.27
    oref
    0.27
    产ä¸ļç»ĵæŀĦ
    0.27
    æ°¸ä¹ħ
    0.26
     permanently
    0.26
    ",-
    0.25
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.24
    ÑģÑĤвеннÑĭе
    0.24
    lef
    0.24
    ç»ĵæŀĦè°ĥæķ´
    0.24
    Activations Density 0.133%

    No Known Activations