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. 128068
    Prev
    Next
    INDEX
    Explanations

    Biobanks and biorepositories

    np_max-act · gemini-2.0-flash
    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
    alin
    -0.07
     pad
    -0.07
    รม
    -0.06
     cantidad
    -0.06
    Amy
    -0.06
     thi
    -0.06
     toe
    -0.06
     التي
    -0.06
     Владимир
    -0.06
    borrow
    -0.06
    POSITIVE LOGITS
    creation
    0.07
     squid
    0.07
     berk
    0.07
    _detach
    0.07
     rotations
    0.07
    strlen
    0.06
     forums
    0.06
    checkpoint
    0.06
    kes
    0.06
     Diane
    0.06
    Activations Density 0.020%

    No Known Activations