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. 2804
    Prev
    Next
    INDEX
    Explanations

    ::

    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
     Kerr
    -0.08
    urm
    -0.07
    clus
    -0.07
    🐾
    -0.07
    @property
    -0.07
     dors
    -0.07
    (send
    -0.07
    莫斯
    -0.07
    飞
    -0.07
     Mos
    -0.06
    POSITIVE LOGITS
     fragmented
    0.07
    \HttpFoundation
    0.07
     impedance
    0.06
    贯
    0.06
    province
    0.06
    (InputStream
    0.06
    伣
    0.06
    在线
    0.06
     hạn
    0.06
     phrases
    0.06
    Activations Density 0.002%

    No Known Activations