© 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. 109115
    Prev
    Next
    INDEX
    Explanations

    Comparisons and analogies

    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
    è¿Ļä¸ĢçĤ¹
    -0.33
    è¿ĻçĤ¹
    -0.29
    clipse
    -0.26
    uristic
    -0.26
    è¿Ļæł·ä¸Ģ
    -0.25
    -season
    -0.25
    owanie
    -0.25
    formance
    -0.25
    EO
    -0.24
    edBy
    -0.24
    POSITIVE LOGITS
     adjacent
    0.29
     adj
    0.27
     Adj
    0.27
     they
    0.26
    缸éĤ»
    0.26
     Set
    0.25
     Kes
    0.25
    (adj
    0.25
     alternatively
    0.24
     someone
    0.24
    Activations Density 0.923%

    No Known Activations