© 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. 23-TRANSCODER-HP
    7. 24722
    Prev
    Next
    INDEX
    Explanations

    possessive "'s"

    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
     interfaces
    -0.27
    è°ģèĥ½
    -0.26
    [s
    -0.26
    æ´Ļ
    -0.25
     spreads
    -0.25
     Ridley
    -0.25
    æ¸IJ
    -0.25
     Recall
    -0.25
    纷纷
    -0.25
    ifest
    -0.24
    POSITIVE LOGITS
    cling
    0.27
    OrCreate
    0.26
    ÑĨе
    0.26
    uhe
    0.25
    ÑĨÑĥ
    0.25
    uble
    0.24
     Org
    0.24
    åħļåĴĮ
    0.24
    cona
    0.24
    clo
    0.24
    Activations Density 0.008%

    No Known Activations