© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 163357
    Prev
    Next
    INDEX
    Explanations

    Diacritics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ="<
    -0.27
    é«ĺæķĪçļĦ
    -0.26
    çĨŁç»ĥ
    -0.26
     sandwich
    -0.25
    mere
    -0.25
    åĽ½ç±į
    -0.25
    loid
    -0.24
    åĿŁ
    -0.24
    reat
    -0.24
    áŀ¶áŀ
    -0.23
    POSITIVE LOGITS
    æĬĢ
    0.29
     vent
    0.29
    çĥĽ
    0.28
    鼨
    0.28
    åıįä¹ĭ
    0.27
    缸åıį
    0.27
    æľīè¿ĩ
    0.27
    å½ķ
    0.26
    åĨ²
    0.25
    .GetInt
    0.25
    Activations Density 0.040%

    No Known Activations