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. 71647
    Prev
    Next
    INDEX
    Explanations

    Sub

    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
     READ
    -0.08
    SocketAddress
    -0.08
    	raise
    -0.07
     MessageBoxIcon
    -0.07
    cast
    -0.07
     lock
    -0.07
    ジョ
    -0.07
    ibold
    -0.07
     Aid
    -0.07
     foster
    -0.07
    POSITIVE LOGITS
     Sub
    0.09
     subsequ
    0.07
     substitution
    0.07
    .sub
    0.07
     sub
    0.07
    =subprocess
    0.07
    わからない
    0.07
    后的
    0.07
     subcontract
    0.07
    clusions
    0.07
    Activations Density 0.100%

    No Known Activations