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

    Neuronpedia

    APICircuit 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. 36317
    Prev
    Next
    INDEX
    Explanations

    Prices and fees

    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
    (display
    -0.07
    _cum
    -0.07
    (inputs
    -0.07
    subset
    -0.07
     veget
    -0.06
    .plot
    -0.06
    _wrap
    -0.06
     Beautiful
    -0.06
    _pas
    -0.06
    :',
    -0.06
    POSITIVE LOGITS
     לשנות
    0.08
    .EditValue
    0.07
    แนะ
    0.07
    ᾰ
    0.07
     believes
    0.07
    县级
    0.07
     нельз
    0.07
     obras
    0.07
    อำนวยความ
    0.07
    مديرية
    0.07
    Activations Density 0.008%

    No Known Activations