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. 11-RESID-POST-AA
    6. 25808
    Prev
    Next
    INDEX
    Explanations

    Reading/watching all the way through

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ٳ
    -0.08
    LocalizedMessage
    -0.08
    璥
    -0.07
    BootTest
    -0.07
    cae
    -0.07
    澥
    -0.07
    ay
    -0.06
    bootstrap
    -0.06
     Monday
    -0.06
     autos
    -0.06
    POSITIVE LOGITS
    有几个
    0.08
    �
    0.07
    誰
    0.07
    一句话
    0.07
    综合利用
    0.07
     fq
    0.07
     북한
    0.07
     בלי
    0.07
     jc
    0.07
    いく
    0.07
    Activations Density 0.052%

    No Known Activations