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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 14475
    Prev
    Next
    INDEX
    Explanations

    sea

    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
     ways
    -0.07
    脈
    -0.06
     ore
    -0.06
     Tender
    -0.06
     fill
    -0.06
    teachers
    -0.06
    ẽ
    -0.06
     Ways
    -0.06
    ��
    -0.06
     honesty
    -0.06
    POSITIVE LOGITS
    шая
    0.07
    -zero
    0.07
    亲近
    0.07
    חבורה
    0.07
     Middleton
    0.07
    初三
    0.07
    -thread
    0.07
    irectional
    0.07
     Stockholm
    0.07
     decking
    0.07
    Activations Density 0.007%

    No Known Activations