© 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. 150268
    Prev
    Next
    INDEX
    Explanations

    County

    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
     поÑĤÑĢебиÑĤел
    -0.27
    isa
    -0.25
    arrison
    -0.24
    @store
    -0.24
    æĶ¿åĬ¡æľįåĬ¡
    -0.24
    åĪĨéĴŁåIJİ
    -0.24
    ritten
    -0.24
    apes
    -0.24
    pace
    -0.23
     regime
    -0.23
    POSITIVE LOGITS
    éĢĥèĦ±
    0.28
    å±Ĥåĩº
    0.26
    æ¹ĸåĮĹçľģ
    0.25
    éĢĥ离
    0.25
    解åĨ³
    0.25
    éĺij
    0.25
    .ma
    0.25
    ernals
    0.24
    平衡
    0.24
    éĻķ西çľģ
    0.24
    Activations Density 0.920%

    No Known Activations