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. 59449
    Prev
    Next
    INDEX
    Explanations

    cell or list

    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
    Nonce
    -0.08
     Flake
    -0.07
    UID
    -0.07
    banner
    -0.07
    ablo
    -0.07
     Citation
    -0.07
    乙烯
    -0.06
    порт
    -0.06
    Inf
    -0.06
     Lid
    -0.06
    POSITIVE LOGITS
     האמריק
    0.06
     그래서
    0.06
     avoided
    0.06
     alarming
    0.06
     MATLAB
    0.06
     rat
    0.06
    린
    0.06
     Mak
    0.06
     MU
    0.06
     مواقع
    0.06
    Activations Density 0.005%

    No Known Activations