© 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. 3083
    Prev
    Next
    INDEX
    Explanations

    public

    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
     encountered
    -0.08
    芑
    -0.07
     Explosion
    -0.07
    疃
    -0.07
     Pistol
    -0.07
     Propel
    -0.07
     plunder
    -0.07
    _command
    -0.07
     voks
    -0.06
    bean
    -0.06
    POSITIVE LOGITS
    方形
    0.07
     Ağ
    0.07
    .grey
    0.07
     SF
    0.07
     limit
    0.07
    geh
    0.06
     publish
    0.06
     sg
    0.06
    逻辑
    0.06
    지는
    0.06
    Activations Density 0.007%

    No Known Activations