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. 31115
    Prev
    Next
    INDEX
    Explanations

    0

    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
    עצב
    -0.07
     차
    -0.07
     vice
    -0.07
     Appeals
    -0.07
     있을
    -0.07
    𝕖
    -0.07
     Федерации
    -0.07
     Encoder
    -0.07
    ᠩ
    -0.07
     לבין
    -0.06
    POSITIVE LOGITS
     rankings
    0.08
    标杆
    0.07
     varied
    0.06
    媛
    0.06
    probe
    0.06
     TIM
    0.06
    表扬
    0.06
    -errors
    0.06
    铝
    0.06
    ellar
    0.06
    Activations Density 0.002%

    No Known Activations