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. 57396
    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
    キャンペ
    -0.07
    휙
    -0.07
     Elon
    -0.07
     Annual
    -0.07
    灯火
    -0.07
    䴔
    -0.07
     freezing
    -0.07
    ൾ
    -0.07
    חק
    -0.06
    oken
    -0.06
    POSITIVE LOGITS
     neurons
    0.07
    oir
    0.07
     glue
    0.07
    "One
    0.07
    bb
    0.07
     appBar
    0.07
    fontSize
    0.07
    "-
    0.07
     fav
    0.07
    kernel
    0.07
    Activations Density 0.001%

    No Known Activations