Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 60195
    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
    好奇心
    -0.07
    (rd
    -0.07
     cấp
    -0.07
    菽
    -0.07
    recommend
    -0.06
    榫
    -0.06
    uku
    -0.06
     Mvc
    -0.06
     master
    -0.06
    customer
    -0.06
    POSITIVE LOGITS
    �
    0.07
     ogó
    0.07
     bron
    0.06
    איר
    0.06
    רד
    0.06
    很高
    0.06
    בעל
    0.06
    걸
    0.06
    也不会
    0.06
     Например
    0.06
    Activations Density 0.020%

    No Known Activations