© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 89882
    Prev
    Next
    INDEX
    Explanations

    Production rates or quantities

    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
     moved
    -0.07
    克
    -0.07
    vary
    -0.06
    斯基
    -0.06
    𝘩
    -0.06
     actions
    -0.06
     😉↵↵
    -0.06
     Shadows
    -0.06
    影
    -0.06
    مان
    -0.06
    POSITIVE LOGITS
    ernetes
    0.07
    (code
    0.07
    operands
    0.07
     Polymer
    0.07
    raft
    0.07
     freelancer
    0.07
     (++
    0.07
     Quý
    0.07
     certified
    0.07
    .customer
    0.07
    Activations Density 0.051%

    No Known Activations