Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 43859
    Prev
    Next
    INDEX
    Explanations

    Image

    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
    ᑐ
    -0.07
     returnValue
    -0.07
    (angle
    -0.07
    -vector
    -0.07
    朏
    -0.06
    .club
    -0.06
    \Eloquent
    -0.06
    (length
    -0.06
     ruled
    -0.06
     Penguins
    -0.06
    POSITIVE LOGITS
    Scaled
    0.07
    Systems
    0.07
    ],↵
    0.07
    Java
    0.07
     transports
    0.07
    Including
    0.07
     striking
    0.07
    IAM
    0.07
     mounting
    0.07
     rev
    0.07
    Activations Density 0.139%

    No Known Activations