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. 7226
    Prev
    Next
    INDEX
    Explanations

    can

    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
    olicies
    -0.07
    ecs
    -0.07
    сал
    -0.07
    保定
    -0.07
    杓
    -0.07
    gium
    -0.07
    有很多
    -0.07
    uzz
    -0.07
    chnitt
    -0.07
     novice
    -0.07
    POSITIVE LOGITS
     Unt
    0.07
     Ultr
    0.07
    �
    0.07
    Rating
    0.07
     сайт
    0.07
    .Byte
    0.06
     earthly
    0.06
    olver
    0.06
     Their
    0.06
    Евро
    0.06
    Activations Density 0.018%

    No Known Activations