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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15-RESID-POST-AA
    6. 26240
    Prev
    Next
    INDEX
    Explanations

    Code separators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Store
    -0.07
    眩
    -0.07
     bold
    -0.07
    hid
    -0.07
    痴
    -0.07
    .Code
    -0.07
    貸
    -0.06
     Vote
    -0.06
     ')
    -0.06
    必然
    -0.06
    POSITIVE LOGITS
    など
    0.07
     Utils
    0.07
    Ҝ
    0.07
    assed
    0.06
    _WRAPPER
    0.06
    igans
    0.06
    .addRow
    0.06
    مواد
    0.06
    などが
    0.06
    ORDER
    0.06
    Activations Density 0.004%

    No Known Activations