© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 76677
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ṇ
    -0.08
    话语
    -0.07
    	ll
    -0.07
    fa
    -0.07
    忍
    -0.07
    消
    -0.07
     invite
    -0.07
    嗔
    -0.07
    chedule
    -0.07
    inness
    -0.07
    POSITIVE LOGITS
    可视
    0.08
     SINGLE
    0.07
    쉈
    0.07
    を目
    0.07
    	SP
    0.07
     TOD
    0.06
     Dial
    0.06
     worms
    0.06
    -seat
    0.06
    :@{
    0.06
    Activations Density 0.012%

    No Known Activations