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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 68869
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     Zug
    -0.08
    ʦ
    -0.07
     الأه
    -0.07
     Hacker
    -0.07
    CED
    -0.07
    ﻸ
    -0.07
    ᠢ
    -0.07
    う
    -0.07
     Helm
    -0.07
     squad
    -0.07
    POSITIVE LOGITS
    .From
    0.08
    aterial
    0.07
     shuffled
    0.07
     puppies
    0.07
    רופא
    0.07
    أفل
    0.07
    小于
    0.07
     perverse
    0.07
     pst
    0.07
    üß
    0.07
    Activations Density 0.015%

    No Known Activations