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. 15-RESID-POST-AA
    6. 56389
    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    当前
    -0.08
     אביב
    -0.08
    触
    -0.07
    睫
    -0.07
    展现了
    -0.07
    <Button
    -0.07
     sunt
    -0.07
    宁夏
    -0.07
     touted
    -0.07
    .zone
    -0.07
    POSITIVE LOGITS
    om
    0.07
     Someone
    0.07
    olor
    0.07
    =index
    0.07
    ا�
    0.06
     Flower
    0.06
    distance
    0.06
     grading
    0.06
    倾听
    0.06
    gorithm
    0.06
    Activations Density 0.001%

    No Known Activations