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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19-RESID-POST-AA
    6. 71796
    Prev
    Next
    INDEX
    Explanations

    Rule

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    游玩
    -0.08
     centr
    -0.07
    "),
    ↵
    -0.07
    ness
    -0.07
     Deaths
    -0.07
    xFFFFFFFF
    -0.06
     resett
    -0.06
    钓鱼
    -0.06
    精细化
    -0.06
     malaysia
    -0.06
    POSITIVE LOGITS
    記者
    0.07
    _POWER
    0.07
    经纪人
    0.06
     EX
    0.06
    (func
    0.06
     expedition
    0.06
    Target
    0.06
    也是非常
    0.06
    VALUE
    0.06
    Convertible
    0.06
    Activations Density 0.000%

    No Known Activations