© 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
    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. 89661
    Prev
    Next
    INDEX
    Explanations

    offensive language

    np_max-act · gemini-2.0-flash
    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
     lúc
    -0.07
    .tell
    -0.07
    buzz
    -0.06
    érique
    -0.06
    cover
    -0.06
    /news
    -0.06
    ア
    -0.06
    ✍
    -0.06
     reign
    -0.06
    iedade
    -0.06
    POSITIVE LOGITS
    (effect
    0.07
    型
    0.07
    ban
    0.07
     accelerated
    0.07
     dependent
    0.07
     BED
    0.07
                            
    0.06
    (CL
    0.06
     pairing
    0.06
    联盟
    0.06
    Activations Density 0.020%

    No Known Activations