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. 45555
    Prev
    Next
    INDEX
    Explanations

    Chinese poetry

    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
     getItem
    -0.08
     retrieved
    -0.07
    Iss
    -0.07
     Cas
    -0.07
     RedirectTo
    -0.07
    血糖
    -0.07
    刁
    -0.07
    䐀
    -0.07
    牵
    -0.07
    급
    -0.07
    POSITIVE LOGITS
    ᘄ
    0.07
    APTER
    0.07
    בלע
    0.07
    ,tmp
    0.07
    应在
    0.07
    贩
    0.06
    nesota
    0.06
     websites
    0.06
     probabil
    0.06
    匙
    0.06
    Activations Density 0.010%

    No Known Activations