© 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
    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. 110080
    Prev
    Next
    INDEX
    Explanations

    It

    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
     disclosing
    -0.07
     ceux
    -0.07
    让大家
    -0.07
    VBoxLayout
    -0.07
    货币政策
    -0.07
    也让
    -0.07
     getDate
    -0.07
    使用者
    -0.06
    Lastly
    -0.06
    领域的
    -0.06
    POSITIVE LOGITS
    -I
    0.07
    _par
    0.07
    余
    0.07
    䴖
    0.07
    -rest
    0.07
     good
    0.07
    -margin
    0.06
     favors
    0.06
    -->
    0.06
    _base
    0.06
    Activations Density 0.040%

    No Known Activations