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. 88174
    Prev
    Next
    INDEX
    Explanations

    Ingredients or allergens

    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
    .OP
    -0.08
    .methods
    -0.07
    .Mock
    -0.07
    这一点
    -0.07
    感慨
    -0.06
    .High
    -0.06
    אוכל
    -0.06
     après
    -0.06
    𬬱
    -0.06
     insulting
    -0.06
    POSITIVE LOGITS
     Brian
    0.07
     UPLOAD
    0.07
     Flags
    0.07
    �
    0.07
    แข
    0.06
     invit
    0.06
    bp
    0.06
    ESC
    0.06
     tamb
    0.06
    一杯
    0.06
    Activations Density 0.020%

    No Known Activations