© 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. 162560
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Il
    -0.27
    pled
    -0.27
    adle
    -0.26
     kitt
    -0.25
    ilib
    -0.25
    _Il
    -0.24
    isNaN
    -0.24
    éĩĩ
    -0.24
    EDURE
    -0.24
    gable
    -0.23
    POSITIVE LOGITS
    fax
    0.26
    storm
    0.26
    vi
    0.25
    èĩªå·±
    0.24
    fare
    0.24
    fort
    0.24
    éĺ´éĺ³
    0.24
    éļıæŶéļıåľ°
    0.23
     emergencies
    0.23
    зо
    0.23
    Activations Density 0.015%

    No Known Activations

    This feature has no known activations.