© 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. 150667
    Prev
    Next
    INDEX
    Explanations

    the

    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
    omba
    -0.27
    éĴĴ
    -0.26
    lore
    -0.26
    è§Ĩ
    -0.25
    parator
    -0.25
     debates
    -0.24
    åĽ°å¢ĥ
    -0.24
    cp
    -0.24
    lef
    -0.23
    etic
    -0.23
    POSITIVE LOGITS
     CCT
    0.27
     sund
    0.27
    aac
    0.26
    æŀģé«ĺ
    0.25
    å°Ĩåħ¶
    0.25
     wykon
    0.24
    suit
    0.24
     setattr
    0.24
    åįģ足
    0.24
    没æĶ¶
    0.24
    Activations Density 0.019%

    No Known Activations