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. 56664
    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
     poo
    -0.08
    .system
    -0.07
    ሴ
    -0.07
    рма
    -0.07
    rich
    -0.07
    уществ
    -0.07
     entail
    -0.07
    댕
    -0.07
    俅
    -0.07
     дальн
    -0.06
    POSITIVE LOGITS
    writer
    0.08
    CancelButton
    0.07
     adjusting
    0.07
    嫣
    0.07
    好像是
    0.07
    BC
    0.06
    	Data
    0.06
     unsafe
    0.06
     affidavit
    0.06
    شعب
    0.06
    Activations Density 0.634%

    No Known Activations