© 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. 150071
    Prev
    Next
    INDEX
    Explanations

    actions or events

    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
    inters
    -0.29
    ican
    -0.28
    ève
    -0.26
     obey
    -0.26
    eman
    -0.26
     sooner
    -0.25
    ŀ
    -0.24
    urgeon
    -0.24
    itr
    -0.23
    ickest
    -0.23
    POSITIVE LOGITS
    Âł
    0.28
     disclosure
    0.28
    flow
    0.27
    å¼ķèµ·äºĨ
    0.27
     revealed
    0.26
    éľ²
    0.26
    æĬ«éľ²
    0.26
     Yet
    0.25
    oni
    0.25
    otp
    0.25
    Activations Density 0.207%

    No Known Activations