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. 6764
    Prev
    Next
    INDEX
    Explanations

    3

    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
    比亚
    -0.08
    JV
    -0.07
     לחצו
    -0.07
    :n
    -0.07
    诲
    -0.07
    ⇆
    -0.06
    校园
    -0.06
     forced
    -0.06
    ﮪ
    -0.06
    𬘯
    -0.06
    POSITIVE LOGITS
     upro
    0.08
     methyl
    0.07
    催化剂
    0.07
     pys
    0.07
     segreg
    0.07
    ROOT
    0.07
    公认的
    0.07
     preferably
    0.07
     ostr
    0.07
    otonin
    0.07
    Activations Density 0.022%

    No Known Activations