© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 8823
    Prev
    Next
    INDEX
    Explanations

    The Walking Dead/Last of Us

    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
    髓
    -0.08
    続
    -0.07
    (DateTime
    -0.07
    心血
    -0.07
    describe
    -0.07
     بك
    -0.07
     gấp
    -0.07
    中共
    -0.07
    之中
    -0.07
    ⌦
    -0.07
    POSITIVE LOGITS
    新人玩家
    0.08
     Wii
    0.07
    预案
    0.07
     مواقع
    0.07
    velopment
    0.07
    anner
    0.07
     Ronnie
    0.07
    ainers
    0.07
     Anim
    0.06
    ussions
    0.06
    Activations Density 0.050%

    No Known Activations