© 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. 25-TRANSCODER-HP
    7. 108440
    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_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uggle
    -0.29
    åİ»è¿ĩ
    -0.26
     ÑģиÑĤÑĥаÑĨии
    -0.24
     joking
    -0.24
     demonstrations
    -0.23
    åĵĦ
    -0.23
    渥
    -0.23
     Majority
    -0.23
    å¿įåıĹ
    -0.23
     humiliation
    -0.22
    POSITIVE LOGITS
    çĩĥæ°Ķ
    0.28
     solid
    0.27
     finally
    0.27
    åĽº
    0.27
     negatively
    0.25
    FX
    0.25
    çķĻ
    0.25
    iterals
    0.25
    :relative
    0.24
    fx
    0.24
    Activations Density 1.086%

    No Known Activations