Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 35781
    Prev
    Next
    INDEX
    Explanations

    "For what it's worth"

    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
    んですよ
    -0.08
    厌恶
    -0.07
    MaxLength
    -0.07
    .magnitude
    -0.07
     atop
    -0.07
    主角
    -0.07
     confuse
    -0.07
     nome
    -0.07
     citing
    -0.07
     دق
    -0.06
    POSITIVE LOGITS
    acker
    0.07
    ונות
    0.07
     Điểm
    0.07
    樣
    0.07
    Prop
    0.07
    ことができる
    0.07
    申花
    0.07
    攒
    0.07
    isory
    0.07
    Minimal
    0.07
    Activations Density 0.008%

    No Known Activations