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. 129562
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    參與
    -0.07
    [value
    -0.07
    �
    -0.07
    此時
    -0.06
     hiện
    -0.06
    ர
    -0.06
    (IN
    -0.06
    .EditValue
    -0.06
     pray
    -0.06
    variable
    -0.06
    POSITIVE LOGITS
    .ModelForm
    0.06
     sacked
    0.06
    -resistant
    0.06
    縢
    0.06
     Wellington
    0.06
     abstract
    0.06
    etric
    0.06
    Altern
    0.06
    荻
    0.06
     Москвы
    0.06
    Activations Density 0.070%

    No Known Activations